diff --git a/config.json b/config.json index 0184b23e1186670b0c867e82606993d3e282e395..bbff6bb63336ba1d46266311fae204d7a2f0afe4 100644 --- a/config.json +++ b/config.json @@ -85,7 +85,7 @@ ], "partial_rotary_factor": 0.25, "rope_theta": 10000000, - "type": "default" + "rope_type": "default" }, "router_aux_loss_coef": 0.001, "shared_expert_intermediate_size": 512, @@ -97,6 +97,22 @@ "torch_dtype": "bfloat16", "transformers_version": "4.57.0.dev0", "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 27, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_5_moe", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2048, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, "vision_end_token_id": 248054, "vision_start_token_id": 248053 } diff --git a/hf_upload_request.json b/hf_upload_request.json index 259cc43d34d17407f18899753ba0d0c95e78921d..74c19c9f2493341eb6f98eedb15810f1d100f335 100644 --- a/hf_upload_request.json +++ b/hf_upload_request.json @@ -3,5 +3,5 @@ "model_id": "agents-a1-4bit", "model_path": "/Users/mike/Desktop/EXO/mlx-to-vllm-export/outputs/agents-a1-4bit-text-dequant-bf16", "repo_id": "exolabs/agents-a1-4bit-text-dequant-bf16", - "uploaded_at_unix": 1783355304 + "uploaded_at_unix": 1783358617 } diff --git a/mlx_to_vllm_export.json b/mlx_to_vllm_export.json index 8419976631e12cd21edde54d4fb00ef08ecc3c74..38aa6dd400927a8c5afd5cbf586455a03d6c2020 100644 --- a/mlx_to_vllm_export.json +++ b/mlx_to_vllm_export.json @@ -3,7 +3,7 @@ "removed": {}, "torch_dtype": "bfloat16" }, - "created_at": "2026-07-06T15:34:00.864475+00:00", + "created_at": "2026-07-06T17:23:24.207531+00:00", "dtype": "bfloat16", "mlx_lm_command": [ "/Users/mike/Desktop/EXO/mlx-to-vllm-export/.venv312/bin/python", diff --git a/model-00001-of-00033.safetensors b/model-00001-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22934a05a5b3ff13b05760e9a679592228ae6c3a --- /dev/null +++ b/model-00001-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccec70675d003a1ffd3024494849e475d96729295848876f1f642531cfc0947 +size 2146843224 diff --git a/model-00001-of-00042.safetensors b/model-00001-of-00042.safetensors deleted file mode 100644 index c88c111b9488a1547d82eb6a88a7e2571040071e..0000000000000000000000000000000000000000 --- a/model-00001-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:50a20b16c6e67fb844bb5dfe6274b4fe517b6b9c8363f7d162523c0222c3b277 -size 1091906016 diff --git a/model-00002-of-00033.safetensors b/model-00002-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d12d9ce1d0f04aa6cc773166beede7fc7b19e16 --- /dev/null +++ b/model-00002-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad0799ad7c0d44a81705b329f426f59694e7eee29446d081e2fdefe670e2730 +size 2146913904 diff --git a/model-00002-of-00042.safetensors b/model-00002-of-00042.safetensors deleted file mode 100644 index 1cc32a92ff311cfff1897430b1dd381f4ce62450..0000000000000000000000000000000000000000 --- a/model-00002-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f638cdfb9704c882b2a7fcbfca258b62a7432fa9aaf54ceeb1b9f7223df72658 -size 1685404408 diff --git a/model-00003-of-00033.safetensors b/model-00003-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a6895b32e57adad0b5884ac68ce74b3aed10362 --- /dev/null +++ b/model-00003-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49e18c0d3a2b5e16414ff59c96f7874e9191a5e70c66bf3efc1a5bc062ce181 +size 2145877792 diff --git a/model-00003-of-00042.safetensors b/model-00003-of-00042.safetensors deleted file mode 100644 index bd23c130b37ae3d82006ccd3088c9fd8a3892ab7..0000000000000000000000000000000000000000 --- a/model-00003-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5c76cb99bc85dbad36edfcdc809d2b870578368a18fd0f94b26f82822f05fd0a -size 1685408640 diff --git a/model-00004-of-00033.safetensors b/model-00004-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fddc7d133f9f14f66643a8def31e1b2e33028474 --- /dev/null +++ b/model-00004-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba32a6c6e67b6647500dcf9493a09c691881e14d0e792f9f3a6752258def8468 +size 2146911912 diff --git a/model-00004-of-00042.safetensors b/model-00004-of-00042.safetensors deleted file mode 100644 index cd7420cf14e07b880cb991e505f80455ba186f2b..0000000000000000000000000000000000000000 --- a/model-00004-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a1a3af0f8c868ff5118f8b4f49ed3a7c75fb4f26158e95eb70498b6cd93a71d6 -size 1617962072 diff --git a/model-00005-of-00033.safetensors b/model-00005-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59765d3b033345ec3f7f12f9ed9ab640b990beeb --- /dev/null +++ b/model-00005-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:509b035fd6bc2c7c79dbf3c3d7379e298a7099256082bb1588876d8ea1018942 +size 2146918136 diff --git a/model-00005-of-00042.safetensors b/model-00005-of-00042.safetensors deleted file mode 100644 index d98ee5637618e94267689406d7490c7ec0bbdfc4..0000000000000000000000000000000000000000 --- a/model-00005-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:11c8970ff8b19d31ab55cef13a1d0f606f89d85c9404e8b7568c2fab68928d38 -size 1739932168 diff --git a/model-00006-of-00033.safetensors b/model-00006-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf3a63701b6d9b93d624e79dddeb0c5a98ff11e1 --- /dev/null +++ b/model-00006-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e30cc1e18629d49e22d70602c9b87d363556cf5899a4ca5c27949ae68dfcfc +size 2145873704 diff --git a/model-00006-of-00042.safetensors b/model-00006-of-00042.safetensors deleted file mode 100644 index f64e8401573c0b4f4aa08b93296936f82ccb3df9..0000000000000000000000000000000000000000 --- a/model-00006-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b26033c07db40d28bed237cddf277e50392beec83a474a9bb9ac9f1f65b7ca29 -size 1685408640 diff --git a/model-00007-of-00033.safetensors b/model-00007-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e89dc9b62cc22cd9deb3f8a8bbfbaa8d7eb96ee5 --- /dev/null +++ b/model-00007-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003e7f98b455d10e74ceed5092ae75412d436c8d0c8445bfe8214a29f6df34a2 +size 2146196792 diff --git a/model-00007-of-00042.safetensors b/model-00007-of-00042.safetensors deleted file mode 100644 index 7b95d6d459dcaac20342e3472936772459245d9b..0000000000000000000000000000000000000000 --- a/model-00007-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0c0c8684cee17ab317413834d5e29592edb16d93ff642a1f74ef06ac2a7797eb -size 1685400176 diff --git a/model-00008-of-00033.safetensors b/model-00008-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d3550ab19ce5e11a293da008e6b086adbb1c004 --- /dev/null +++ b/model-00008-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55bc0ec7daf65b52839c15a5777b0112aac62c6d595c878ed015618fd39f4b40 +size 2146591960 diff --git a/model-00008-of-00042.safetensors b/model-00008-of-00042.safetensors deleted file mode 100644 index fbe0e81410d83c282a6e5a4e1284ab3feac6ff78..0000000000000000000000000000000000000000 --- a/model-00008-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:673be034b19d2919eb9265dc8c06dc543dc8515baaa33fdff715a082ea7f4939 -size 1617966304 diff --git a/model-00009-of-00033.safetensors b/model-00009-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8aebe6e224ff2e30a4148e559a7324067e8a59d6 --- /dev/null +++ b/model-00009-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c7a0ae1d7735c0a0556869636b3377b7430da22209fc8ee2ea14bd5cc25321 +size 2146909672 diff --git a/model-00009-of-00042.safetensors b/model-00009-of-00042.safetensors deleted file mode 100644 index 1450040b911e3c6ac97d04b3ce53d6095b3f5177..0000000000000000000000000000000000000000 --- a/model-00009-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b1c5198b0affe7880e2cfb895aa4f37ba8e318b6e3821b14b95c064201ffa5d3 -size 1808427344 diff --git a/model-00010-of-00033.safetensors b/model-00010-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc4e4466889acdafe8b4d5ad413bc4abf3ef0ef8 --- /dev/null +++ b/model-00010-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af568e97f5e2fdb195ac8519f5ea7c1a39f23096113e7c0dfa4d8b13867f22bf +size 2146918856 diff --git a/model-00010-of-00042.safetensors b/model-00010-of-00042.safetensors deleted file mode 100644 index 504ae6242839fa9cba951d0b9a470f4acb64e031..0000000000000000000000000000000000000000 --- a/model-00010-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a6354705bc999d4d25d865ab6dfe8bbcc71eaa66c2eac7c8b3897607bc205b6f -size 1672498296 diff --git a/model-00011-of-00033.safetensors b/model-00011-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13b414ac4a67300f16336e04d850c86a668c1da4 --- /dev/null +++ b/model-00011-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d278493154323f44bf1b9823c75d3d5a23c2ac42730ced25d3173d790491a0 +size 2146914656 diff --git a/model-00011-of-00042.safetensors b/model-00011-of-00042.safetensors deleted file mode 100644 index 67f9bae34868dd65bc89c86e15d63b8dd548962a..0000000000000000000000000000000000000000 --- a/model-00011-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ef5be633a74c862e757598b3e25439536895a43b83af5460d57148318ad475f4 -size 1685400176 diff --git a/model-00012-of-00033.safetensors b/model-00012-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..910b619a7be2820faac00e58a9af6ff620985f00 --- /dev/null +++ b/model-00012-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82cfc08fac45e3c1bca6849c39fb023bd906e7b695f0323a0588665bc0a6d09b +size 2146919112 diff --git a/model-00012-of-00042.safetensors b/model-00012-of-00042.safetensors deleted file mode 100644 index e727a15f1e82c97620fb47b726b64343ca7c9323..0000000000000000000000000000000000000000 --- a/model-00012-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0105ea5e850c6339efb2e86643f736fe38c4089252faf941afa020d884dc49c1 -size 1616913360 diff --git a/model-00013-of-00033.safetensors b/model-00013-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2eb8d55d4ca791a6c18b911bea91d2f43fa910b2 --- /dev/null +++ b/model-00013-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e419d48299e0bc073367f2fbbe0447f174c0d598baa7af78793ac88679716065 +size 2138201208 diff --git a/model-00013-of-00042.safetensors b/model-00013-of-00042.safetensors deleted file mode 100644 index 52bdb34639dd408074bb585b7729be3e2eecd843..0000000000000000000000000000000000000000 --- a/model-00013-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cc0b6e9b05a3d6a485bfed8f76e75425716408d1c0e1d2314e0487d4a9e3dfd9 -size 1685400200 diff --git a/model-00014-of-00033.safetensors b/model-00014-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..799ebaf48bf688468a02fa1b0d8c9eae47357af8 --- /dev/null +++ b/model-00014-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29cac4abe145f530788ee3d62eb731a6a2cf4009df6371f2219a4ee3e6d828a +size 2146201560 diff --git a/model-00014-of-00042.safetensors b/model-00014-of-00042.safetensors deleted file mode 100644 index 956d9dec5335e985e4e6397cf17c487499fe92b1..0000000000000000000000000000000000000000 --- a/model-00014-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3c3bf471bd3f839ff8eb0f091f8ea533dd920b17002dcba094a4dc511efebd00 -size 1685404432 diff --git a/model-00015-of-00033.safetensors b/model-00015-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19cb909ddf8132982e82212546b0eeb6013f7e45 --- /dev/null +++ b/model-00015-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412a921ad21194001a7fc51a3c3308af15d17de9b82356233583fc639b7c7013 +size 2146910496 diff --git a/model-00015-of-00042.safetensors b/model-00015-of-00042.safetensors deleted file mode 100644 index 7c16eab54ce883561f246eda1d4bd047e55d3511..0000000000000000000000000000000000000000 --- a/model-00015-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:76ea3458ae5947d11d9bda7f2fff2a49828a9f636a118ec0f4b1bab52454be8b -size 1685408664 diff --git a/model-00016-of-00033.safetensors b/model-00016-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a62de99e1ef1b25fca3cab3b3f4b88deb2f35fd8 --- /dev/null +++ b/model-00016-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5eb4a7c603543093dbe7c465d724659d7ed230f6c3fda1f4bc53027ae7e2333 +size 2146590096 diff --git a/model-00016-of-00042.safetensors b/model-00016-of-00042.safetensors deleted file mode 100644 index c46734486356c450ade375d65652febf4505500f..0000000000000000000000000000000000000000 --- a/model-00016-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:538fb626305d5f3cf863c1f490a6caa61a814972b38b694b99e26da54f75ef63 -size 1617962080 diff --git a/model-00017-of-00033.safetensors b/model-00017-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61157efbe29e11c5624f1a4228d5a78c80f276a5 --- /dev/null +++ b/model-00017-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b5093e3b5697817dea0a7713d6421dd45aaa12df662b58a8642112f9ebd32c +size 2146201912 diff --git a/model-00017-of-00042.safetensors b/model-00017-of-00042.safetensors deleted file mode 100644 index 9ad01d5e900eab1c29d2bf213c5e17431e464cd4..0000000000000000000000000000000000000000 --- a/model-00017-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1d955e0ff12be0eda92a3502b4bb5ffbf66f4a28282d67f29887557dd2aafaca -size 1739932192 diff --git a/model-00018-of-00033.safetensors b/model-00018-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16169fe5187b132cb6b3ca61dec393583cd928c4 --- /dev/null +++ b/model-00018-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69172f613de4c7a8373d287f7b583411105f8fa16d6044468faf79a5a0b7529 +size 2146914640 diff --git a/model-00018-of-00042.safetensors b/model-00018-of-00042.safetensors deleted file mode 100644 index 1adae63bf66919b4f98d1e254ce8d3d4a00458e4..0000000000000000000000000000000000000000 --- a/model-00018-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4d98cf9c82921dbbb07306860c2a01ba23c90bf8a267f39a867b1263607dc64d -size 1685408664 diff --git a/model-00019-of-00033.safetensors b/model-00019-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ded74fcaa8693a658c6f704c1dd9d83a9310a9a --- /dev/null +++ b/model-00019-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b22705e1429ae44d7360baa0802b7d8b1b9fffe6bb249f9c7f62b3e6d4fe48 +size 2146592440 diff --git a/model-00019-of-00042.safetensors b/model-00019-of-00042.safetensors deleted file mode 100644 index 182eae9493440bf334762725a4a6839ec8c1fd2b..0000000000000000000000000000000000000000 --- a/model-00019-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:80dbb411f6e9f26862ed5a3af1e81f7316afbbd4f6257303a7a4c675afe1b888 -size 1685400200 diff --git a/model-00020-of-00033.safetensors b/model-00020-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e3ddd0ae31a129f0e3304db9d0fa400f9c554ef --- /dev/null +++ b/model-00020-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88eab003afae570e473f3897bd29eef9984d6f1f29532c49b8d315fed8d1cd7 +size 2146910672 diff --git a/model-00020-of-00042.safetensors b/model-00020-of-00042.safetensors deleted file mode 100644 index 46f4a3b9070c8d8c2837748d367195f6bc2dcef2..0000000000000000000000000000000000000000 --- a/model-00020-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:675737d12154812ba194fad25d907d0dab0a035ce8cd80840d1b74fb45dbc0b1 -size 1617966312 diff --git a/model-00021-of-00033.safetensors b/model-00021-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e54fa1cfb9ad0b32a91426298079713bf4581f84 --- /dev/null +++ b/model-00021-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e2c64c5f768d2660bbb1a625d33bfd077ba0d59283a59260244192e9d7e82d +size 2146207864 diff --git a/model-00021-of-00042.safetensors b/model-00021-of-00042.safetensors deleted file mode 100644 index 8c8b4c3de66bafb5530137454e398dc5a6016ffa..0000000000000000000000000000000000000000 --- a/model-00021-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9c0c3f8b4c75669907b808b0689b928feaada083b54fe1b0b8f0ffc78a21ebfc -size 1739936424 diff --git a/model-00022-of-00033.safetensors b/model-00022-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bea5324e81aeb1f73d732e7d47213e5c93fe3cec --- /dev/null +++ b/model-00022-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed6afc1d7bd70c222a390dd16a032183d10728e0810506f5b20bc9928afef26 +size 2146585680 diff --git a/model-00022-of-00042.safetensors b/model-00022-of-00042.safetensors deleted file mode 100644 index 4e38b73d9d6726d63e0241fd13382c2fde1f7d2f..0000000000000000000000000000000000000000 --- a/model-00022-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7e3f51f84c404762ba73b2620eb6ef4ada10aab2e2b595ce61ba28203019b1dd -size 1685400200 diff --git a/model-00023-of-00033.safetensors b/model-00023-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab69791bccf1e2a1b90bd9936beea82c542165da --- /dev/null +++ b/model-00023-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a085fe50e34637fd531f3464c4f4892f579991782411d8728e220a00e7fbf56 +size 2146913104 diff --git a/model-00023-of-00042.safetensors b/model-00023-of-00042.safetensors deleted file mode 100644 index fc66349f4cadd9be8bf4f075383564f3a0903dc0..0000000000000000000000000000000000000000 --- a/model-00023-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:32bdc6954deac11f959d39e97324ec26d83c812b8feef5d86a8bd3b81ceaa3ca -size 1685404432 diff --git a/model-00024-of-00033.safetensors b/model-00024-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ceb79ea57484b0b014ebe70c043c4d94d43b3c0b --- /dev/null +++ b/model-00024-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc0edca390a4872c17c34afdba9266042c18d828775c6e649309109b32ba242 +size 2128376184 diff --git a/model-00024-of-00042.safetensors b/model-00024-of-00042.safetensors deleted file mode 100644 index cfc0d6147bf91d8f2a08b6f299b884333b60775d..0000000000000000000000000000000000000000 --- a/model-00024-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:62396b8ca94679caec751009d1e1ace02c2e00c04e7c8a80743369cb3a9f87ad -size 1672498304 diff --git a/model-00025-of-00033.safetensors b/model-00025-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..997530985979ecbb464ae4fc259425dd9ea0b135 --- /dev/null +++ b/model-00025-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2632ebedbf0eee6d5177b980b89bea706b5a28df925b442c68dcaed95ac954ba +size 2145541928 diff --git a/model-00025-of-00042.safetensors b/model-00025-of-00042.safetensors deleted file mode 100644 index 04d99332924effd53bb83a9fe2907172bf73badd..0000000000000000000000000000000000000000 --- a/model-00025-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e44db44194cf7cedd8376fdfb89396461e8fd49a82aac9de54113dfcbab6e473 -size 1685400200 diff --git a/model-00026-of-00033.safetensors b/model-00026-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2511f7b44e26dc70c3fe388977c1cb4c61264ab3 --- /dev/null +++ b/model-00026-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fec62b149fc701bcb26752a1250f92a1100960cbac61bfbc412cb3186555299 +size 2146917168 diff --git a/model-00026-of-00042.safetensors b/model-00026-of-00042.safetensors deleted file mode 100644 index 4946f0bb4e29a0e3e7561da99cdb8f687f0c1d98..0000000000000000000000000000000000000000 --- a/model-00026-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f70e94d2e2761a1fd5fdea2059dc59542e591c0aa674c3550d62bcc5451cca80 -size 1685404432 diff --git a/model-00027-of-00033.safetensors b/model-00027-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a209f9261e51ae25598d0e09d22c01c9cd26c17 --- /dev/null +++ b/model-00027-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448d584e3c946ad2c2c9d75d2fcce5415353b6de26f146d26c05620684ea6963 +size 2146910680 diff --git a/model-00027-of-00042.safetensors b/model-00027-of-00042.safetensors deleted file mode 100644 index 3b9d924bf6f4798bf33bb70af4ad538df99f381a..0000000000000000000000000000000000000000 --- a/model-00027-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e5ca08c3119a63e93082e4f366b7fb4229faaf7818e305a42db1359564af9439 -size 1685408664 diff --git a/model-00028-of-00033.safetensors b/model-00028-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b93619f95c05c4809777850fc660b4d2b67c4500 --- /dev/null +++ b/model-00028-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a323d0e5f06f99bcb4c366ca06afc68315d324c2aa3fe2f4ffa47d91a9125e3 +size 2145881320 diff --git a/model-00028-of-00042.safetensors b/model-00028-of-00042.safetensors deleted file mode 100644 index 5640545c38992db07ddf55f94d9eb264ee9ff345..0000000000000000000000000000000000000000 --- a/model-00028-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:47c01546ef9a5eb4ec8bfc4e5f8723882d31db7c086236bf0a0caa5f7c34a69a -size 1617962080 diff --git a/model-00029-of-00033.safetensors b/model-00029-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..501fabb6cb985cb6abf5cd67547d4599e0b6fba6 --- /dev/null +++ b/model-00029-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78f205b9f9ff3ac3f359ece1d5be0c951f291e8c7800f5235d228d49264779d +size 2146910408 diff --git a/model-00029-of-00042.safetensors b/model-00029-of-00042.safetensors deleted file mode 100644 index 89c49e515a11be4671dc92dad4b7f23c42a417fb..0000000000000000000000000000000000000000 --- a/model-00029-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f59fd7d92d17bfca5e4a141ebedd3c003807f2cdb73c046f26815a44e48f5850 -size 1739932192 diff --git a/model-00030-of-00033.safetensors b/model-00030-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9c188df081ea0686cfbbf92fb798d1b7c8f091b --- /dev/null +++ b/model-00030-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e75bcf83d167b8da678cf17fa0ebc92fe404a1c2fde8f7fd8ffaed7b1cee69 +size 2146914840 diff --git a/model-00030-of-00042.safetensors b/model-00030-of-00042.safetensors deleted file mode 100644 index 82e00a30a15227ee66b653c8e8f44e1f117f8c01..0000000000000000000000000000000000000000 --- a/model-00030-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3ee9b748b4036488f6417f54b876c7f350d82084755cb904b4a5648e9c3e6d25 -size 1685408664 diff --git a/model-00031-of-00033.safetensors b/model-00031-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98aadd2a07bf4e9d266c6bd9efde17092048f2d0 --- /dev/null +++ b/model-00031-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02bbe9f9d93d3d0dea5c590631e416ca3a3bd3e2412ae05a0ba931c6dec7762d +size 2146852256 diff --git a/model-00031-of-00042.safetensors b/model-00031-of-00042.safetensors deleted file mode 100644 index c738335220ef2b4b741fdb14f86b0693a598dac1..0000000000000000000000000000000000000000 --- a/model-00031-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:81acfa317769f92e66ef47399b08a7b8f4b6c67ee46ae44ee190fb07ff711aa3 -size 1685400200 diff --git a/model-00032-of-00033.safetensors b/model-00032-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74fc8a9111d482f15857e4c9dd1b3fe26e472093 --- /dev/null +++ b/model-00032-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f5ecb51585c34a3083f8e52fadbfdc09b4e4a346c2b5432c707fecd545de6c +size 2146585792 diff --git a/model-00032-of-00042.safetensors b/model-00032-of-00042.safetensors deleted file mode 100644 index d39505215159c13c356a93658d25992e918f8311..0000000000000000000000000000000000000000 --- a/model-00032-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0edfe7c879255e730001651d45f635fa8553dce9b0ec63dd13fcb7167d1afd9e -size 1617966312 diff --git a/model-00033-of-00033.safetensors b/model-00033-of-00033.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b48d1c4855dfeeebd5e5ddb8ff458503ec9990e1 --- /dev/null +++ b/model-00033-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3c50521e0767bb62990a541a669b1db858d3d712a12885b7dc9aec54bdd6f9 +size 660653016 diff --git a/model-00033-of-00042.safetensors b/model-00033-of-00042.safetensors deleted file mode 100644 index fc2d40f05609bc34b1026a46bc86f38977de5580..0000000000000000000000000000000000000000 --- a/model-00033-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e41f3d9bf67618f11fda0af0e38b0cb7e3454ae926a1163f661176758d4be636 -size 1739936424 diff --git a/model-00034-of-00042.safetensors b/model-00034-of-00042.safetensors deleted file mode 100644 index 6060a0e05d954dce41b2585ce7d9761cf8e88538..0000000000000000000000000000000000000000 --- a/model-00034-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8a0a8f70a18d70150c661364295be86bae3724e41778b6e46e08ad94596d2ef1 -size 1685400200 diff --git a/model-00035-of-00042.safetensors b/model-00035-of-00042.safetensors deleted file mode 100644 index dbe506473697bbe411626d8cdfe7d648586a3704..0000000000000000000000000000000000000000 --- a/model-00035-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bdcf298e09599b864df6fb602f4f425454b27892aa58e3ed7639cba80c66ed0c -size 1685404432 diff --git a/model-00036-of-00042.safetensors b/model-00036-of-00042.safetensors deleted file mode 100644 index 0f9c1c810ed9c709af9e75dbb1b4b6e65775ca61..0000000000000000000000000000000000000000 --- a/model-00036-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3b4e29a7d68edf6581faa0c9cf6a48419e605d4d944154fa07a9ba2599793242 -size 1672498304 diff --git a/model-00037-of-00042.safetensors b/model-00037-of-00042.safetensors deleted file mode 100644 index 71131979dcb75d7d44a939b23dc00b81e3ef414f..0000000000000000000000000000000000000000 --- a/model-00037-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1c82c1cc2b6ffb53f09430a5760c1e1684d9d73d696952d0bb7ab8689e1ca1df -size 1685400200 diff --git a/model-00038-of-00042.safetensors b/model-00038-of-00042.safetensors deleted file mode 100644 index c6bd6b45b6f25b1b41df25b483d15a53bedaf883..0000000000000000000000000000000000000000 --- a/model-00038-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1fd67f993da8801dee2791d9e26fb071047a5dda16c3c759fb4aea7d3dae8372 -size 1685404432 diff --git a/model-00039-of-00042.safetensors b/model-00039-of-00042.safetensors deleted file mode 100644 index 6afe3f292b3c9c3f1180635ca1049cfa8d76f9ec..0000000000000000000000000000000000000000 --- a/model-00039-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6edb35d44c546bfd46537f1f2365603393b16f84c1d70d17d0fe7a9426fe1ad0 -size 1679112544 diff --git a/model-00040-of-00042.safetensors b/model-00040-of-00042.safetensors deleted file mode 100644 index 9e47dc2a34e1a79adfe8b822abc2a6049f2f3044..0000000000000000000000000000000000000000 --- a/model-00040-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bd0adaf28c774983a41099b97a1740a6eae2324ee9b0fe8746706daffac9c4e4 -size 2097156928 diff --git a/model-00041-of-00042.safetensors b/model-00041-of-00042.safetensors deleted file mode 100644 index 357f78d78c9fceefe3e9e08ac5cf5e27e024aa06..0000000000000000000000000000000000000000 --- a/model-00041-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5fc0ae5c3137563fb504550cd46eb31c01ba2fe83a494246254918fdc801c2ff -size 1617962080 diff --git a/model-00042-of-00042.safetensors b/model-00042-of-00042.safetensors deleted file mode 100644 index 35f7621ec76ba1ca8b6da209f214ad8c83543546..0000000000000000000000000000000000000000 --- a/model-00042-of-00042.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:333cf4625a08dd91e0959cd79ff671e2dc25284cbc141238bb074f6e5408cc64 -size 591407256 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index a749f96187416afd5a400dafe88e2ba52b6e664f..76403362d227c2c88bb665064d0b96afda4cb960 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -4,698 +4,31338 @@ "total_size": 69321221376 }, "weight_map": { - "lm_head.weight": "model-00040-of-00042.safetensors", - "model.language_model.embed_tokens.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.mlp.experts.down_proj": "model-00002-of-00042.safetensors", - "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00002-of-00042.safetensors", - "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00042.safetensors", - "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.mlp.experts.down_proj": "model-00003-of-00042.safetensors", - "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00003-of-00042.safetensors", - "model.language_model.layers.1.mlp.gate.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00042.safetensors", - "model.language_model.layers.1.post_attention_layernorm.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.10.input_layernorm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.A_log": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.dt_bias": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.norm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.mlp.experts.down_proj": "model-00010-of-00042.safetensors", - "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00010-of-00042.safetensors", - "model.language_model.layers.10.mlp.gate.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.10.post_attention_layernorm.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.input_layernorm.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.mlp.experts.down_proj": "model-00013-of-00042.safetensors", - "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00013-of-00042.safetensors", - "model.language_model.layers.11.mlp.gate.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00012-of-00042.safetensors", - "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00012-of-00042.safetensors", - "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00012-of-00042.safetensors", - "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00012-of-00042.safetensors", - "model.language_model.layers.11.post_attention_layernorm.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.self_attn.k_norm.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.self_attn.k_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.self_attn.o_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.self_attn.q_norm.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.self_attn.q_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.11.self_attn.v_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.12.input_layernorm.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.A_log": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.dt_bias": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.norm.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.mlp.experts.down_proj": "model-00014-of-00042.safetensors", - "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00014-of-00042.safetensors", - "model.language_model.layers.12.mlp.gate.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00013-of-00042.safetensors", - "model.language_model.layers.12.post_attention_layernorm.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.input_layernorm.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.A_log": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.dt_bias": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.norm.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.mlp.experts.down_proj": "model-00015-of-00042.safetensors", - "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00015-of-00042.safetensors", - "model.language_model.layers.13.mlp.gate.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00014-of-00042.safetensors", - "model.language_model.layers.13.post_attention_layernorm.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.input_layernorm.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.A_log": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.dt_bias": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.norm.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.mlp.experts.down_proj": "model-00016-of-00042.safetensors", - "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00016-of-00042.safetensors", - "model.language_model.layers.14.mlp.gate.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.14.post_attention_layernorm.weight": "model-00015-of-00042.safetensors", - "model.language_model.layers.15.input_layernorm.weight": "model-00016-of-00042.safetensors", - "model.language_model.layers.15.mlp.experts.down_proj": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.mlp.gate.weight": "model-00016-of-00042.safetensors", - "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00016-of-00042.safetensors", - "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00016-of-00042.safetensors", - "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00016-of-00042.safetensors", - "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00016-of-00042.safetensors", - "model.language_model.layers.15.post_attention_layernorm.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.self_attn.k_norm.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.self_attn.k_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.self_attn.o_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.self_attn.q_norm.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.self_attn.q_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.15.self_attn.v_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.input_layernorm.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.A_log": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.dt_bias": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.norm.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.mlp.experts.down_proj": "model-00018-of-00042.safetensors", - "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00018-of-00042.safetensors", - "model.language_model.layers.16.mlp.gate.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00017-of-00042.safetensors", - "model.language_model.layers.16.post_attention_layernorm.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.input_layernorm.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.A_log": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.dt_bias": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.norm.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.mlp.experts.down_proj": "model-00019-of-00042.safetensors", - "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00019-of-00042.safetensors", - "model.language_model.layers.17.mlp.gate.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.17.post_attention_layernorm.weight": "model-00018-of-00042.safetensors", - "model.language_model.layers.18.input_layernorm.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.A_log": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.dt_bias": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.norm.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.mlp.experts.down_proj": "model-00020-of-00042.safetensors", - "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00020-of-00042.safetensors", - "model.language_model.layers.18.mlp.gate.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00019-of-00042.safetensors", - "model.language_model.layers.18.post_attention_layernorm.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.input_layernorm.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.mlp.experts.down_proj": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.mlp.gate.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00020-of-00042.safetensors", - "model.language_model.layers.19.post_attention_layernorm.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.self_attn.k_norm.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.self_attn.k_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.self_attn.o_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.self_attn.q_norm.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.self_attn.q_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.19.self_attn.v_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.2.input_layernorm.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.A_log": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.dt_bias": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.norm.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.mlp.experts.down_proj": "model-00004-of-00042.safetensors", - "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00004-of-00042.safetensors", - "model.language_model.layers.2.mlp.gate.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.2.post_attention_layernorm.weight": "model-00003-of-00042.safetensors", - "model.language_model.layers.20.input_layernorm.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.A_log": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.dt_bias": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.norm.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.mlp.experts.down_proj": "model-00022-of-00042.safetensors", - "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00022-of-00042.safetensors", - "model.language_model.layers.20.mlp.gate.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.20.post_attention_layernorm.weight": "model-00021-of-00042.safetensors", - "model.language_model.layers.21.input_layernorm.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.A_log": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.dt_bias": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.norm.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.mlp.experts.down_proj": "model-00023-of-00042.safetensors", - "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00023-of-00042.safetensors", - "model.language_model.layers.21.mlp.gate.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00022-of-00042.safetensors", - "model.language_model.layers.21.post_attention_layernorm.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.input_layernorm.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.A_log": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.dt_bias": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.norm.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.mlp.experts.down_proj": "model-00024-of-00042.safetensors", - "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00024-of-00042.safetensors", - "model.language_model.layers.22.mlp.gate.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00023-of-00042.safetensors", - "model.language_model.layers.22.post_attention_layernorm.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.input_layernorm.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.mlp.experts.down_proj": "model-00025-of-00042.safetensors", - "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00025-of-00042.safetensors", - "model.language_model.layers.23.mlp.gate.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.post_attention_layernorm.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.self_attn.k_norm.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.self_attn.k_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.self_attn.o_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.self_attn.q_norm.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.self_attn.q_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.23.self_attn.v_proj.weight": "model-00024-of-00042.safetensors", - "model.language_model.layers.24.input_layernorm.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.A_log": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.dt_bias": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.norm.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.mlp.experts.down_proj": "model-00026-of-00042.safetensors", - "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00026-of-00042.safetensors", - "model.language_model.layers.24.mlp.gate.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00025-of-00042.safetensors", - "model.language_model.layers.24.post_attention_layernorm.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.input_layernorm.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.A_log": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.dt_bias": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.norm.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.mlp.experts.down_proj": "model-00027-of-00042.safetensors", - "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00027-of-00042.safetensors", - "model.language_model.layers.25.mlp.gate.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00026-of-00042.safetensors", - "model.language_model.layers.25.post_attention_layernorm.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.input_layernorm.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.A_log": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.dt_bias": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.norm.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.mlp.experts.down_proj": "model-00028-of-00042.safetensors", - "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00028-of-00042.safetensors", - "model.language_model.layers.26.mlp.gate.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.26.post_attention_layernorm.weight": "model-00027-of-00042.safetensors", - "model.language_model.layers.27.input_layernorm.weight": "model-00028-of-00042.safetensors", - "model.language_model.layers.27.mlp.experts.down_proj": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.mlp.gate.weight": "model-00028-of-00042.safetensors", - "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00028-of-00042.safetensors", - "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00028-of-00042.safetensors", - "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00028-of-00042.safetensors", - "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00028-of-00042.safetensors", - "model.language_model.layers.27.post_attention_layernorm.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.self_attn.k_norm.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.self_attn.k_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.self_attn.o_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.self_attn.q_norm.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.self_attn.q_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.27.self_attn.v_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.input_layernorm.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.A_log": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.dt_bias": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.norm.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.mlp.experts.down_proj": "model-00030-of-00042.safetensors", - "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00030-of-00042.safetensors", - "model.language_model.layers.28.mlp.gate.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00029-of-00042.safetensors", - "model.language_model.layers.28.post_attention_layernorm.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.input_layernorm.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.A_log": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.dt_bias": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.norm.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.mlp.experts.down_proj": "model-00031-of-00042.safetensors", - "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00031-of-00042.safetensors", - "model.language_model.layers.29.mlp.gate.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.29.post_attention_layernorm.weight": "model-00030-of-00042.safetensors", - "model.language_model.layers.3.input_layernorm.weight": "model-00004-of-00042.safetensors", - "model.language_model.layers.3.mlp.experts.down_proj": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.mlp.gate.weight": "model-00004-of-00042.safetensors", - "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00004-of-00042.safetensors", - "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00004-of-00042.safetensors", - "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00004-of-00042.safetensors", - "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00004-of-00042.safetensors", - "model.language_model.layers.3.post_attention_layernorm.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.self_attn.k_norm.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.self_attn.k_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.self_attn.o_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.self_attn.q_norm.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.self_attn.q_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.3.self_attn.v_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.30.input_layernorm.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.A_log": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.dt_bias": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.norm.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.mlp.experts.down_proj": "model-00032-of-00042.safetensors", - "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00032-of-00042.safetensors", - "model.language_model.layers.30.mlp.gate.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00031-of-00042.safetensors", - "model.language_model.layers.30.post_attention_layernorm.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.input_layernorm.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.mlp.experts.down_proj": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.mlp.gate.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00032-of-00042.safetensors", - "model.language_model.layers.31.post_attention_layernorm.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.self_attn.k_norm.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.self_attn.k_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.self_attn.o_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.self_attn.q_norm.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.self_attn.q_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.31.self_attn.v_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.input_layernorm.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.A_log": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.dt_bias": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.norm.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.mlp.experts.down_proj": "model-00034-of-00042.safetensors", - "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00034-of-00042.safetensors", - "model.language_model.layers.32.mlp.gate.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.32.post_attention_layernorm.weight": "model-00033-of-00042.safetensors", - "model.language_model.layers.33.input_layernorm.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.A_log": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.dt_bias": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.norm.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.mlp.experts.down_proj": "model-00035-of-00042.safetensors", - "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00035-of-00042.safetensors", - "model.language_model.layers.33.mlp.gate.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00034-of-00042.safetensors", - "model.language_model.layers.33.post_attention_layernorm.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.input_layernorm.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.A_log": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.dt_bias": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.norm.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.mlp.experts.down_proj": "model-00036-of-00042.safetensors", - "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00036-of-00042.safetensors", - "model.language_model.layers.34.mlp.gate.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00035-of-00042.safetensors", - "model.language_model.layers.34.post_attention_layernorm.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.input_layernorm.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.mlp.experts.down_proj": "model-00037-of-00042.safetensors", - "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00037-of-00042.safetensors", - "model.language_model.layers.35.mlp.gate.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.post_attention_layernorm.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.self_attn.k_norm.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.self_attn.k_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.self_attn.o_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.self_attn.q_norm.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.self_attn.q_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.35.self_attn.v_proj.weight": "model-00036-of-00042.safetensors", - "model.language_model.layers.36.input_layernorm.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.A_log": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.dt_bias": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.norm.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.mlp.experts.down_proj": "model-00038-of-00042.safetensors", - "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00038-of-00042.safetensors", - "model.language_model.layers.36.mlp.gate.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00037-of-00042.safetensors", - "model.language_model.layers.36.post_attention_layernorm.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.input_layernorm.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.A_log": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.dt_bias": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.norm.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.mlp.experts.down_proj": "model-00039-of-00042.safetensors", - "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00039-of-00042.safetensors", - "model.language_model.layers.37.mlp.gate.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00038-of-00042.safetensors", - "model.language_model.layers.37.post_attention_layernorm.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.input_layernorm.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.A_log": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.dt_bias": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.norm.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.mlp.experts.down_proj": "model-00041-of-00042.safetensors", - "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00040-of-00042.safetensors", - "model.language_model.layers.38.mlp.gate.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00040-of-00042.safetensors", - "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00040-of-00042.safetensors", - "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00040-of-00042.safetensors", - "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00040-of-00042.safetensors", - "model.language_model.layers.38.post_attention_layernorm.weight": "model-00039-of-00042.safetensors", - "model.language_model.layers.39.input_layernorm.weight": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.mlp.experts.down_proj": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.mlp.gate.weight": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00041-of-00042.safetensors", - "model.language_model.layers.39.post_attention_layernorm.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.self_attn.k_norm.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.self_attn.k_proj.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.self_attn.o_proj.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.self_attn.q_norm.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.self_attn.q_proj.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.39.self_attn.v_proj.weight": "model-00042-of-00042.safetensors", - "model.language_model.layers.4.input_layernorm.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.A_log": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.dt_bias": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.norm.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.mlp.experts.down_proj": "model-00006-of-00042.safetensors", - "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00006-of-00042.safetensors", - "model.language_model.layers.4.mlp.gate.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00005-of-00042.safetensors", - "model.language_model.layers.4.post_attention_layernorm.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.input_layernorm.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.A_log": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.dt_bias": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.norm.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.mlp.experts.down_proj": "model-00007-of-00042.safetensors", - "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00007-of-00042.safetensors", - "model.language_model.layers.5.mlp.gate.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.5.post_attention_layernorm.weight": "model-00006-of-00042.safetensors", - "model.language_model.layers.6.input_layernorm.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.A_log": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.dt_bias": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.norm.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.mlp.experts.down_proj": "model-00008-of-00042.safetensors", - "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00008-of-00042.safetensors", - "model.language_model.layers.6.mlp.gate.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00007-of-00042.safetensors", - "model.language_model.layers.6.post_attention_layernorm.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.input_layernorm.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.mlp.experts.down_proj": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.mlp.gate.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00008-of-00042.safetensors", - "model.language_model.layers.7.post_attention_layernorm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.self_attn.k_norm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.self_attn.k_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.self_attn.o_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.self_attn.q_norm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.self_attn.q_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.7.self_attn.v_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.input_layernorm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.A_log": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.dt_bias": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.norm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.mlp.experts.down_proj": "model-00011-of-00042.safetensors", - "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00011-of-00042.safetensors", - "model.language_model.layers.8.mlp.gate.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00010-of-00042.safetensors", - "model.language_model.layers.8.post_attention_layernorm.weight": "model-00009-of-00042.safetensors", - "model.language_model.layers.9.input_layernorm.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.A_log": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.dt_bias": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.norm.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.mlp.experts.down_proj": "model-00012-of-00042.safetensors", - "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00012-of-00042.safetensors", - "model.language_model.layers.9.mlp.gate.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00011-of-00042.safetensors", - "model.language_model.layers.9.post_attention_layernorm.weight": "model-00012-of-00042.safetensors", - "model.language_model.norm.weight": "model-00042-of-00042.safetensors" + "lm_head.weight": "model-00031-of-00033.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.10.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.10.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.10.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.100.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.100.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.100.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.101.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.101.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.101.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.102.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.102.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.102.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.103.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.103.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.103.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.104.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.104.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.104.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.105.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.105.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.105.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.106.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.106.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.106.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.107.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.107.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.107.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.108.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.108.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.108.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.109.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.109.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.109.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.11.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.11.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.11.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.110.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.110.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.110.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.111.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.111.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.111.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.112.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.112.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.112.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.113.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.113.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.113.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.114.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.114.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.114.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.115.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.115.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.115.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.116.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.116.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.116.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.117.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.117.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.117.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.118.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.118.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.118.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.119.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.119.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.119.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.12.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.12.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.12.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.120.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.120.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.120.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.121.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.121.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.121.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.122.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.122.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.122.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.123.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.123.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.123.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.124.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.124.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.124.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.125.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.125.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.125.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.126.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.126.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.126.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.127.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.127.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.127.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.128.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.128.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.128.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.129.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.129.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.129.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.13.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.13.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.13.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.130.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.130.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.130.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.131.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.131.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.131.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.132.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.132.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.132.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.133.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.133.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.133.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.134.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.134.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.134.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.135.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.135.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.135.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.136.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.136.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.136.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.137.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.137.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.137.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.138.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.138.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.138.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.139.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.139.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.139.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.14.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.14.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.14.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.140.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.140.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.140.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.141.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.141.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.141.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.142.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.142.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.142.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.143.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.143.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.143.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.144.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.144.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.144.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.145.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.145.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.145.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.146.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.146.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.146.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.147.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.147.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.147.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.148.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.148.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.148.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.149.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.149.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.149.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.15.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.15.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.15.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.150.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.150.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.150.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.151.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.151.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.151.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.152.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.152.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.152.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.153.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.153.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.153.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.154.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.154.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.154.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.155.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.155.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.155.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.156.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.156.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.156.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.157.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.157.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.157.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.158.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.158.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.158.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.159.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.159.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.159.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.16.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.16.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.16.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.160.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.160.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.160.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.161.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.161.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.161.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.162.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.162.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.162.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.163.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.163.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.163.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.164.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.164.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.164.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.165.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.165.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.165.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.166.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.166.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.166.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.167.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.167.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.167.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.168.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.168.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.168.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.169.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.169.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.169.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.17.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.17.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.17.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.170.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.170.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.170.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.171.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.171.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.171.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.172.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.172.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.172.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.173.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.173.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.173.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.174.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.174.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.174.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.175.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.175.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.175.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.176.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.176.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.176.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.177.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.177.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.177.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.178.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.178.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.178.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.179.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.179.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.179.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.18.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.18.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.18.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.180.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.180.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.180.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.181.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.181.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.181.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.182.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.182.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.182.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.183.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.183.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.183.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.184.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.184.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.184.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.185.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.185.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.185.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.186.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.186.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.186.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.187.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.187.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.187.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.188.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.188.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.188.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.189.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.189.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.189.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.19.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.19.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.19.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.190.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.190.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.190.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.191.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.191.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.191.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.192.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.192.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.192.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.193.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.193.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.193.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.194.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.194.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.194.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.195.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.195.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.195.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.196.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.196.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.196.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.197.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.197.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.197.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.198.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.198.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.198.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.199.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.199.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.199.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.20.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.20.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.20.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.200.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.200.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.200.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.201.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.201.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.201.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.202.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.202.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.202.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.203.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.203.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.203.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.204.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.204.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.204.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.205.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.205.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.205.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.206.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.206.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.206.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.207.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.207.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.207.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.208.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.208.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.208.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.209.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.209.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.209.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.21.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.21.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.21.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.210.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.210.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.210.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.211.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.211.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.211.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.212.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.212.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.212.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.213.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.213.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.213.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.214.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.214.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.214.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.215.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.215.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.215.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.216.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.216.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.216.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.217.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.217.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.217.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.218.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.218.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.218.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.219.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.219.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.219.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.22.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.22.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.22.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.220.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.220.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.220.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.221.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.221.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.221.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.222.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.222.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.222.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.223.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.223.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.223.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.224.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.224.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.224.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.225.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.225.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.225.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.226.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.226.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.226.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.227.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.227.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.227.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.228.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.228.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.228.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.229.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.229.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.229.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.23.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.23.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.23.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.230.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.230.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.230.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.231.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.231.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.231.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.232.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.232.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.232.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.233.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.233.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.233.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.234.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.234.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.234.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.235.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.235.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.235.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.236.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.236.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.236.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.237.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.237.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.237.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.238.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.238.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.238.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.239.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.239.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.239.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.24.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.24.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.24.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.240.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.240.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.240.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.241.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.241.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.241.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.242.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.242.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.242.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.243.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.243.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.243.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.244.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.244.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.244.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.245.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.245.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.245.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.246.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.246.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.246.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.247.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.247.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.247.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.248.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.248.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.248.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.249.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.249.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.249.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.25.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.25.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.25.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.250.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.250.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.250.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.251.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.251.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.251.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.252.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.252.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.252.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.253.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.253.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.253.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.254.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.254.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.254.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.255.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.255.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.255.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.26.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.26.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.26.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.27.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.27.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.27.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.28.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.28.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.28.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.29.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.29.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.29.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.30.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.30.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.30.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.31.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.31.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.31.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.32.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.32.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.32.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.33.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.33.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.33.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.34.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.34.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.34.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.35.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.35.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.35.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.36.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.36.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.36.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.37.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.37.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.37.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.38.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.38.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.38.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.39.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.39.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.39.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.4.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.4.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.4.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.40.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.40.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.40.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.41.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.41.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.41.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.42.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.42.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.42.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.43.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.43.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.43.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.44.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.44.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.44.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.45.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.45.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.45.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.46.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.46.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.46.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.47.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.47.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.47.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.48.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.48.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.48.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.49.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.49.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.49.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.5.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.5.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.5.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.50.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.50.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.50.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.51.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.51.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.51.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.52.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.52.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.52.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.53.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.53.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.53.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.54.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.54.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.54.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.55.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.55.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.55.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.56.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.56.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.56.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.57.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.57.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.57.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.58.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.58.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.58.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.59.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.59.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.59.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.6.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.6.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.6.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.60.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.60.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.60.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.61.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.61.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.61.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.62.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.62.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.62.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.63.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.63.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.63.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.64.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.64.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.64.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.65.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.65.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.65.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.66.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.66.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.66.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.67.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.67.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.67.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.68.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.68.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.68.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.69.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.69.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.69.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.7.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.7.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.7.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.70.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.70.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.70.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.71.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.71.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.71.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.72.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.72.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.72.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.73.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.73.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.73.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.74.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.74.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.74.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.75.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.75.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.75.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.76.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.76.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.76.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.77.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.77.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.77.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.78.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.78.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.78.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.79.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.79.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.79.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.8.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.8.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.8.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.80.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.80.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.80.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.81.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.81.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.81.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.82.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.82.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.82.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.83.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.83.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.83.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.84.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.84.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.84.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.85.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.85.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.85.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.86.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.86.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.86.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.87.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.87.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.87.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.88.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.88.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.88.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.89.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.89.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.89.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.9.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.9.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.9.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.90.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.90.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.90.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.91.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.91.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.91.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.92.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.92.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.92.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.93.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.93.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.93.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.94.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.94.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.94.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.95.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.95.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.95.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.96.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.96.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.96.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.97.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.97.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.97.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.98.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.98.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.98.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.99.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.99.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.experts.99.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00033.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.10.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.10.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.100.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.100.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.100.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.101.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.101.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.101.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.102.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.102.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.102.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.103.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.103.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.103.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.104.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.104.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.104.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.105.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.105.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.105.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.106.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.106.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.106.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.107.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.107.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.107.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.108.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.108.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.108.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.109.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.109.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.109.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.11.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.11.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.110.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.110.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.110.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.111.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.111.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.111.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.112.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.112.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.112.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.113.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.113.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.113.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.114.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.114.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.114.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.115.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.115.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.115.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.116.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.116.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.116.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.117.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.117.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.117.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.118.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.118.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.118.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.119.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.119.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.119.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.12.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.12.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.120.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.120.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.120.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.121.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.121.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.121.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.122.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.122.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.122.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.123.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.123.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.123.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.124.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.124.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.124.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.125.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.125.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.125.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.126.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.126.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.126.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.127.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.127.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.127.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.128.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.128.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.128.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.129.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.129.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.129.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.13.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.13.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.130.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.130.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.130.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.131.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.131.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.131.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.132.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.132.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.132.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.133.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.133.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.133.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.134.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.134.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.134.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.135.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.135.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.135.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.136.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.136.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.136.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.137.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.137.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.137.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.138.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.138.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.138.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.139.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.139.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.139.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.14.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.14.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.140.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.140.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.140.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.141.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.141.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.141.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.142.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.142.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.142.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.143.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.143.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.143.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.144.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.144.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.144.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.145.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.145.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.145.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.146.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.146.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.146.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.147.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.147.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.147.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.148.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.148.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.148.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.149.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.149.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.149.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.15.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.15.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.150.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.150.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.150.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.151.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.151.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.151.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.152.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.152.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.152.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.153.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.153.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.153.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.154.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.154.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.154.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.155.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.155.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.155.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.156.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.156.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.156.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.157.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.157.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.157.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.158.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.158.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.158.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.159.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.159.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.159.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.16.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.16.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.160.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.160.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.160.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.161.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.161.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.161.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.162.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.162.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.162.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.163.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.163.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.163.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.164.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.164.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.164.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.165.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.165.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.165.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.166.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.166.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.166.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.167.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.167.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.167.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.168.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.168.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.168.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.169.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.169.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.169.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.17.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.17.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.170.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.170.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.170.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.171.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.171.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.171.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.172.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.172.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.172.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.173.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.173.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.173.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.174.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.174.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.174.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.175.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.175.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.175.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.176.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.176.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.176.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.177.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.177.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.177.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.178.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.178.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.178.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.179.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.179.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.179.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.18.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.18.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.180.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.180.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.180.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.181.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.181.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.181.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.182.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.182.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.182.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.183.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.183.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.183.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.184.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.184.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.184.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.185.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.185.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.185.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.186.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.186.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.186.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.187.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.187.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.187.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.188.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.188.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.188.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.189.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.189.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.189.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.19.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.19.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.190.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.190.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.190.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.191.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.191.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.191.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.192.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.192.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.192.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.193.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.193.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.193.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.194.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.194.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.194.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.195.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.195.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.195.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.196.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.196.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.196.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.197.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.197.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.197.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.198.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.198.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.198.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.199.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.199.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.199.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.20.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.20.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.200.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.200.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.200.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.201.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.201.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.201.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.202.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.202.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.202.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.203.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.203.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.203.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.204.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.204.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.204.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.205.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.205.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.205.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.206.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.206.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.206.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.207.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.207.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.207.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.208.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.208.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.208.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.209.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.209.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.209.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.21.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.21.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.210.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.210.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.210.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.211.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.211.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.211.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.212.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.212.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.212.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.213.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.213.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.213.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.214.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.214.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.214.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.215.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.215.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.215.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.216.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.216.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.216.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.217.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.217.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.217.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.218.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.218.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.218.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.219.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.219.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.219.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.22.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.22.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.220.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.220.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.220.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.221.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.221.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.221.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.222.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.222.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.222.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.223.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.223.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.223.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.224.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.224.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.224.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.225.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.225.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.225.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.226.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.226.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.226.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.227.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.227.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.227.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.228.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.228.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.228.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.229.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.229.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.229.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.23.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.23.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.230.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.230.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.230.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.231.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.231.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.231.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.232.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.232.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.232.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.233.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.233.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.233.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.234.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.234.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.234.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.235.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.235.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.235.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.236.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.236.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.236.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.237.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.237.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.237.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.238.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.238.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.238.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.239.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.239.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.239.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.24.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.24.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.240.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.240.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.240.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.241.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.241.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.241.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.242.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.242.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.242.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.243.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.243.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.243.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.244.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.244.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.244.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.245.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.245.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.245.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.246.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.246.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.246.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.247.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.247.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.247.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.248.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.248.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.248.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.249.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.249.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.249.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.25.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.250.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.250.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.250.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.251.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.251.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.251.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.252.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.252.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.252.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.253.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.253.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.253.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.254.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.254.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.254.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.255.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.255.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.255.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.26.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.26.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.27.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.27.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.28.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.28.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.29.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.29.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.30.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.30.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.31.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.31.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.32.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.32.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.33.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.33.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.34.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.34.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.35.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.35.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.36.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.37.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.38.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.39.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.40.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.41.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.42.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.43.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.44.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.45.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.46.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.47.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.48.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.49.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.50.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.51.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.52.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.53.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.54.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.55.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.56.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.57.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.58.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.64.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.64.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.64.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.65.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.65.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.65.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.66.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.66.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.66.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.67.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.67.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.67.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.68.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.68.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.68.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.69.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.69.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.69.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.70.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.70.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.70.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.71.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.71.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.71.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.72.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.72.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.72.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.73.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.73.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.73.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.74.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.74.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.74.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.75.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.75.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.75.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.76.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.76.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.76.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.77.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.77.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.77.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.78.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.78.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.78.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.79.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.79.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.79.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.8.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.80.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.80.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.80.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.81.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.81.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.81.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.82.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.82.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.82.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.83.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.83.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.83.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.84.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.84.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.84.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.85.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.85.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.85.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.86.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.86.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.86.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.87.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.87.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.87.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.88.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.88.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.88.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.89.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.89.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.9.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.90.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.90.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.90.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.91.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.91.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.91.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.92.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.92.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.93.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.93.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.93.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.94.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.94.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.94.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.95.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.95.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.95.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.96.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.96.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.96.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.97.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.97.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.97.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.98.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.98.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.98.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.99.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.99.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.experts.99.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.gate.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00033.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.A_log": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.dt_bias": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.norm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.0.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.0.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.0.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.1.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.1.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.1.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.10.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.10.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.10.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.100.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.100.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.100.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.101.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.101.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.101.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.102.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.102.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.102.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.103.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.103.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.103.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.104.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.104.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.104.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.105.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.105.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.105.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.106.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.106.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.106.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.107.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.107.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.107.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.108.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.108.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.108.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.109.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.109.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.109.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.11.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.11.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.11.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.110.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.110.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.110.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.111.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.111.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.111.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.112.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.112.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.112.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.113.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.113.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.113.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.114.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.114.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.114.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.115.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.115.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.115.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.116.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.116.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.116.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.117.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.117.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.117.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.118.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.118.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.118.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.119.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.119.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.119.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.12.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.12.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.12.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.120.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.120.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.120.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.121.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.121.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.121.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.122.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.122.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.122.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.123.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.123.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.123.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.124.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.124.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.124.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.125.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.125.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.125.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.126.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.126.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.126.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.127.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.127.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.127.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.128.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.128.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.128.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.129.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.129.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.129.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.13.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.13.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.13.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.130.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.130.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.130.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.131.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.131.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.131.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.132.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.132.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.132.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.133.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.133.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.133.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.134.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.134.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.134.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.135.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.135.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.135.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.136.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.136.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.136.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.137.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.137.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.137.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.138.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.138.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.138.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.139.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.139.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.139.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.14.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.14.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.14.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.140.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.140.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.140.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.141.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.141.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.141.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.142.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.142.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.142.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.143.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.143.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.143.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.144.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.144.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.144.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.145.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.145.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.145.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.146.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.146.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.146.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.147.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.147.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.147.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.148.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.148.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.148.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.149.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.149.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.149.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.15.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.15.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.15.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.150.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.150.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.150.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.151.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.151.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.151.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.152.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.152.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.152.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.153.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.153.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.153.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.154.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.154.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.154.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.155.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.155.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.155.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.156.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.156.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.156.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.157.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.157.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.157.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.158.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.158.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.158.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.159.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.159.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.159.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.16.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.16.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.16.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.160.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.160.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.160.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.161.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.161.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.161.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.162.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.162.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.162.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.163.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.163.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.163.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.164.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.164.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.164.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.165.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.165.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.165.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.166.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.166.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.166.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.167.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.167.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.167.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.168.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.168.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.168.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.169.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.169.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.169.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.17.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.17.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.17.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.170.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.170.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.170.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.171.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.171.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.171.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.172.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.172.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.172.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.173.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.173.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.173.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.174.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.174.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.174.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.175.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.175.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.175.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.176.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.176.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.176.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.177.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.177.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.177.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.178.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.178.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.178.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.179.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.179.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.179.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.18.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.18.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.18.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.180.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.180.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.180.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.181.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.181.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.181.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.182.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.182.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.182.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.183.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.183.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.183.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.184.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.184.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.184.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.185.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.185.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.185.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.186.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.186.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.186.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.187.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.187.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.187.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.188.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.188.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.188.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.189.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.189.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.189.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.19.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.19.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.19.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.190.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.190.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.190.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.191.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.191.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.191.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.192.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.192.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.192.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.193.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.193.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.193.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.194.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.194.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.194.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.195.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.195.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.195.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.196.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.196.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.196.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.197.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.197.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.197.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.198.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.198.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.198.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.199.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.199.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.199.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.2.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.2.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.2.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.20.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.20.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.20.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.200.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.200.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.200.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.201.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.201.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.201.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.202.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.202.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.202.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.203.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.203.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.203.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.204.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.204.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.204.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.205.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.205.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.205.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.206.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.206.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.206.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.207.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.207.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.207.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.208.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.208.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.208.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.209.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.209.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.209.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.21.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.21.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.21.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.210.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.210.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.210.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.211.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.211.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.211.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.212.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.212.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.212.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.213.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.213.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.213.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.214.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.214.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.214.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.215.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.215.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.215.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.216.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.216.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.216.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.217.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.217.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.217.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.218.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.218.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.218.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.219.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.219.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.219.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.22.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.22.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.22.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.220.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.220.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.220.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.221.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.221.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.221.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.222.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.222.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.222.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.223.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.223.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.223.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.224.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.224.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.224.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.225.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.225.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.225.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.226.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.226.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.226.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.227.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.227.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.227.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.228.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.228.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.228.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.229.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.229.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.229.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.23.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.23.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.23.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.230.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.230.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.230.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.231.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.231.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.231.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.232.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.232.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.232.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.233.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.233.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.233.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.234.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.234.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.234.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.235.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.235.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.235.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.236.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.236.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.236.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.237.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.237.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.237.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.238.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.238.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.238.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.239.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.239.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.239.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.24.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.24.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.24.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.240.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.240.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.240.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.241.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.241.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.241.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.242.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.242.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.242.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.243.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.243.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.243.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.244.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.244.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.244.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.245.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.245.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.245.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.246.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.246.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.246.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.247.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.247.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.247.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.248.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.248.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.248.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.249.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.249.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.249.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.25.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.25.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.25.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.250.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.250.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.250.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.251.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.251.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.251.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.252.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.252.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.252.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.253.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.253.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.253.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.254.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.254.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.254.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.255.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.255.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.255.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.26.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.26.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.26.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.27.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.27.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.27.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.28.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.28.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.28.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.29.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.29.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.29.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.3.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.3.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.3.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.30.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.30.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.30.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.31.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.31.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.31.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.32.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.32.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.32.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.33.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.33.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.33.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.34.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.34.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.34.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.35.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.35.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.35.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.36.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.36.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.36.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.37.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.37.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.37.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.38.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.38.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.38.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.39.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.39.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.39.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.4.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.4.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.4.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.40.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.40.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.40.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.41.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.41.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.41.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.42.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.42.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.42.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.43.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.43.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.43.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.44.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.44.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.44.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.45.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.45.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.45.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.46.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.46.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.46.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.47.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.47.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.47.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.48.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.48.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.48.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.49.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.49.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.49.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.5.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.5.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.5.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.50.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.50.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.50.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.51.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.51.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.51.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.52.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.52.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.52.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.53.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.53.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.53.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.54.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.54.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.54.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.55.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.55.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.55.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.56.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.56.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.56.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.57.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.57.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.57.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.58.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.58.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.58.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.59.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.59.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.59.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.6.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.6.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.6.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.60.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.60.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.60.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.61.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.61.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.61.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.62.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.62.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.62.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.63.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.63.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.63.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.64.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.64.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.64.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.65.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.65.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.65.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.66.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.66.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.66.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.67.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.67.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.67.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.68.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.68.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.68.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.69.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.69.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.69.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.7.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.7.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.7.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.70.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.70.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.70.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.71.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.71.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.71.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.72.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.72.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.72.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.73.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.73.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.73.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.74.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.74.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.74.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.75.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.75.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.75.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.76.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.76.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.76.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.77.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.77.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.77.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.78.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.78.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.78.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.79.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.79.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.79.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.8.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.8.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.8.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.80.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.80.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.80.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.81.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.81.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.81.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.82.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.82.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.82.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.83.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.83.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.83.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.84.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.84.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.84.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.85.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.85.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.85.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.86.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.86.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.86.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.87.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.87.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.87.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.88.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.88.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.88.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.89.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.89.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.89.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.9.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.9.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.9.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.90.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.90.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.90.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.91.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.91.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.91.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.92.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.92.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.92.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.93.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.93.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.93.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.94.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.94.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.94.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.95.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.95.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.95.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.96.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.96.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.96.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.97.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.97.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.97.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.98.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.98.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.98.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.99.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.99.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.experts.99.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.10.mlp.gate.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.0.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.0.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.0.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.1.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.1.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.1.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.10.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.10.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.10.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.100.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.100.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.100.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.101.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.101.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.101.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.102.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.102.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.102.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.103.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.103.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.103.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.104.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.104.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.104.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.105.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.105.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.105.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.106.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.106.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.106.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.107.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.107.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.107.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.108.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.108.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.108.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.109.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.109.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.109.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.11.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.11.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.11.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.110.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.110.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.110.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.111.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.111.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.111.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.112.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.112.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.112.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.113.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.113.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.113.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.114.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.114.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.114.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.115.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.115.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.115.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.116.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.116.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.116.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.117.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.117.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.117.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.118.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.118.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.118.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.119.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.119.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.119.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.12.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.12.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.12.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.120.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.120.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.120.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.121.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.121.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.121.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.122.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.122.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.122.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.123.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.123.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.123.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.124.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.124.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.124.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.125.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.125.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.125.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.126.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.126.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.126.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.127.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.127.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.127.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.128.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.128.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.128.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.129.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.129.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.129.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.13.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.13.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.13.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.130.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.130.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.130.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.131.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.131.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.131.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.132.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.132.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.132.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.133.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.133.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.133.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.134.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.134.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.134.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.135.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.135.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.135.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.136.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.136.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.136.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.137.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.137.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.137.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.138.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.138.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.138.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.139.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.139.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.139.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.14.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.14.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.14.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.140.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.140.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.140.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.141.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.141.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.141.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.142.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.142.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.142.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.143.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.143.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.143.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.144.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.144.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.144.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.145.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.145.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.145.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.146.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.146.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.146.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.147.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.147.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.147.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.148.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.148.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.148.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.149.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.149.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.149.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.15.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.15.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.15.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.150.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.150.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.150.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.151.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.151.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.151.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.152.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.152.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.152.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.153.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.153.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.153.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.154.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.154.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.154.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.155.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.155.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.155.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.156.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.156.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.156.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.157.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.157.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.157.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.158.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.158.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.158.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.159.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.159.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.159.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.16.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.16.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.16.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.160.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.160.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.160.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.161.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.161.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.161.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.162.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.162.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.162.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.163.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.163.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.163.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.164.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.164.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.164.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.165.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.165.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.165.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.166.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.166.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.166.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.167.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.167.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.167.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.168.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.168.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.168.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.169.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.169.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.169.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.17.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.17.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.17.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.170.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.170.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.170.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.171.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.171.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.171.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.172.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.172.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.172.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.173.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.173.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.173.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.174.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.174.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.174.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.175.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.175.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.175.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.176.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.176.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.176.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.177.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.177.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.177.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.178.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.178.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.178.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.179.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.179.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.179.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.18.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.18.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.18.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.180.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.180.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.180.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.181.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.181.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.181.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.182.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.182.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.182.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.183.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.183.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.183.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.184.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.184.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.184.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.185.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.185.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.185.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.186.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.186.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.186.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.187.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.187.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.187.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.188.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.188.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.188.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.189.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.189.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.189.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.19.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.19.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.19.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.190.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.190.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.190.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.191.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.191.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.191.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.192.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.192.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.192.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.193.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.193.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.193.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.194.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.194.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.194.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.195.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.195.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.195.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.196.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.196.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.196.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.197.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.197.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.197.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.198.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.198.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.198.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.199.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.199.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.199.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.2.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.2.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.2.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.20.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.20.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.20.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.200.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.200.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.200.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.201.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.201.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.201.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.202.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.202.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.202.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.203.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.203.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.203.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.204.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.204.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.204.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.205.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.205.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.205.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.206.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.206.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.206.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.207.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.207.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.207.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.208.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.208.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.208.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.209.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.209.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.209.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.21.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.21.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.21.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.210.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.210.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.210.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.211.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.211.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.211.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.212.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.212.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.212.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.213.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.213.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.213.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.214.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.214.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.214.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.215.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.215.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.215.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.216.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.216.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.216.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.217.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.217.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.217.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.218.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.218.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.218.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.219.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.219.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.219.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.22.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.22.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.22.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.220.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.220.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.220.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.221.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.221.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.221.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.222.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.222.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.222.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.223.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.223.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.223.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.224.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.224.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.224.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.225.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.225.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.225.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.226.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.226.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.226.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.227.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.227.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.227.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.228.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.228.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.228.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.229.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.229.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.229.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.23.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.23.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.23.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.230.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.230.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.230.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.231.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.231.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.231.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.232.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.232.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.232.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.233.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.233.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.233.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.234.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.234.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.234.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.235.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.235.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.235.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.236.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.236.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.236.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.237.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.237.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.237.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.238.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.238.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.238.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.239.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.239.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.239.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.24.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.24.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.24.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.240.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.240.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.240.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.241.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.241.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.241.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.242.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.242.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.242.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.243.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.243.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.243.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.244.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.244.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.244.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.245.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.245.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.245.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.246.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.246.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.246.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.247.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.247.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.247.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.248.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.248.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.248.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.249.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.249.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.249.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.25.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.25.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.25.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.250.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.250.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.250.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.251.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.251.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.251.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.252.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.252.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.252.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.253.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.253.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.253.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.254.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.254.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.254.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.255.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.255.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.255.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.26.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.26.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.26.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.27.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.27.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.27.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.28.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.28.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.28.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.29.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.29.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.29.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.3.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.3.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.3.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.30.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.30.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.30.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.31.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.31.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.31.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.32.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.32.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.32.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.33.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.33.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.33.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.34.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.34.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.34.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.35.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.35.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.35.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.36.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.36.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.36.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.37.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.37.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.37.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.38.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.38.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.38.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.39.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.39.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.39.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.4.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.4.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.4.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.40.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.40.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.40.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.41.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.41.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.41.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.42.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.42.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.42.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.43.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.43.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.43.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.44.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.44.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.44.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.45.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.45.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.45.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.46.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.46.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.46.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.47.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.47.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.47.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.48.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.48.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.48.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.49.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.49.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.49.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.5.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.5.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.5.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.50.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.50.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.50.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.51.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.51.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.51.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.52.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.52.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.52.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.53.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.53.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.53.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.54.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.54.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.54.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.55.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.55.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.55.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.56.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.56.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.56.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.57.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.57.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.57.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.58.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.58.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.58.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.59.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.59.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.59.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.6.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.6.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.6.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.60.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.60.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.60.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.61.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.61.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.61.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.62.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.62.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.62.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.63.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.63.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.63.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.64.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.64.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.64.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.65.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.65.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.65.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.66.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.66.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.66.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.67.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.67.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.67.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.68.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.68.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.68.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.69.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.69.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.69.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.7.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.7.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.7.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.70.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.70.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.70.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.71.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.71.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.71.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.72.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.72.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.72.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.73.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.73.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.73.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.74.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.74.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.74.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.75.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.75.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.75.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.76.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.76.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.76.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.77.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.77.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.77.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.78.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.78.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.78.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.79.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.79.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.79.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.8.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.8.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.8.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.80.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.80.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.80.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.81.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.81.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.81.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.82.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.82.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.82.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.83.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.83.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.83.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.84.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.84.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.84.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.85.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.85.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.85.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.86.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.86.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.86.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.87.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.87.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.87.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.88.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.88.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.88.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.89.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.89.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.89.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.9.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.9.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.9.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.90.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.90.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.90.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.91.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.91.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.91.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.92.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.92.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.92.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.93.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.93.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.93.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.94.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.94.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.94.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.95.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.95.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.95.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.96.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.96.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.96.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.97.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.97.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.97.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.98.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.98.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.98.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.99.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.99.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.experts.99.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.gate.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.A_log": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.dt_bias": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.norm.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.0.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.0.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.0.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.1.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.1.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.1.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.10.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.10.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.10.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.100.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.100.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.100.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.101.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.101.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.101.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.102.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.102.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.102.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.103.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.103.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.103.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.104.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.104.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.104.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.105.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.105.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.105.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.106.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.106.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.106.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.107.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.107.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.107.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.108.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.108.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.108.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.109.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.109.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.109.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.11.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.11.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.11.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.110.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.110.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.110.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.111.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.111.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.111.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.112.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.112.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.112.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.113.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.113.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.113.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.114.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.114.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.114.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.115.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.115.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.115.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.116.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.116.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.116.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.117.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.117.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.117.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.118.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.118.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.118.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.119.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.119.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.119.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.12.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.12.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.12.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.120.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.120.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.120.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.121.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.121.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.121.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.122.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.122.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.122.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.123.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.123.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.123.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.124.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.124.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.124.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.125.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.125.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.125.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.126.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.126.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.126.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.127.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.127.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.127.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.128.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.128.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.128.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.129.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.129.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.129.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.13.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.13.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.13.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.130.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.130.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.130.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.131.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.131.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.131.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.132.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.132.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.132.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.133.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.133.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.133.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.134.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.134.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.134.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.135.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.135.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.135.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.136.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.136.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.136.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.137.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.137.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.137.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.138.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.138.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.138.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.139.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.139.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.139.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.14.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.14.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.14.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.140.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.140.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.140.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.141.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.141.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.141.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.142.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.142.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.142.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.143.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.143.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.143.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.144.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.144.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.144.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.145.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.145.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.145.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.146.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.146.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.146.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.147.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.147.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.147.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.148.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.148.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.148.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.149.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.149.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.149.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.15.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.15.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.15.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.150.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.150.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.150.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.151.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.151.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.151.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.152.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.152.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.152.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.153.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.153.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.153.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.154.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.154.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.154.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.155.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.155.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.155.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.156.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.156.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.156.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.157.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.157.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.157.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.158.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.158.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.158.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.159.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.159.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.159.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.16.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.16.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.16.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.160.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.160.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.160.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.161.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.161.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.161.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.162.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.162.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.162.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.163.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.163.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.163.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.164.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.164.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.164.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.165.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.165.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.165.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.166.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.166.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.166.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.167.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.167.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.167.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.168.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.168.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.168.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.169.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.169.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.169.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.17.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.17.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.17.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.170.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.170.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.170.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.171.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.171.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.171.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.172.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.172.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.172.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.173.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.173.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.173.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.174.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.174.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.174.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.175.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.175.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.175.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.176.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.176.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.176.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.177.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.177.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.177.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.178.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.178.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.178.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.179.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.179.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.179.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.18.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.18.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.18.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.180.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.180.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.180.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.181.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.181.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.181.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.182.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.182.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.182.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.183.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.183.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.183.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.184.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.184.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.184.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.185.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.185.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.185.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.186.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.186.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.186.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.187.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.187.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.187.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.188.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.188.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.188.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.189.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.189.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.189.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.19.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.19.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.19.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.190.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.190.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.190.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.191.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.191.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.191.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.192.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.192.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.192.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.193.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.193.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.193.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.194.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.194.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.194.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.195.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.195.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.195.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.196.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.196.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.196.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.197.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.197.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.197.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.198.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.198.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.198.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.199.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.199.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.199.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.2.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.2.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.2.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.20.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.20.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.20.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.200.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.200.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.200.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.201.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.201.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.201.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.202.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.202.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.202.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.203.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.203.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.203.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.204.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.204.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.204.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.205.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.205.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.205.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.206.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.206.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.206.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.207.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.207.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.207.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.208.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.208.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.208.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.209.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.209.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.209.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.21.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.21.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.21.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.210.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.210.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.210.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.211.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.211.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.211.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.212.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.212.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.212.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.213.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.213.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.213.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.214.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.214.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.214.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.215.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.215.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.215.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.216.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.216.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.216.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.217.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.217.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.217.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.218.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.218.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.218.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.219.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.219.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.219.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.22.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.22.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.22.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.220.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.220.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.220.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.221.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.221.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.221.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.222.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.222.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.222.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.223.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.223.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.223.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.224.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.224.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.224.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.225.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.225.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.225.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.226.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.226.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.226.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.227.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.227.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.227.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.228.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.228.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.228.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.229.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.229.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.229.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.23.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.23.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.23.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.230.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.230.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.230.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.231.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.231.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.231.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.232.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.232.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.232.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.233.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.233.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.233.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.234.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.234.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.234.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.235.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.235.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.235.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.236.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.236.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.236.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.237.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.237.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.237.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.238.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.238.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.238.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.239.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.239.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.239.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.24.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.24.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.24.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.240.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.240.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.240.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.241.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.241.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.241.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.242.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.242.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.242.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.243.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.243.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.243.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.244.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.244.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.244.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.245.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.245.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.245.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.246.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.246.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.246.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.247.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.247.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.247.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.248.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.248.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.248.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.249.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.249.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.249.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.25.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.25.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.25.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.250.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.250.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.250.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.251.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.251.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.251.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.252.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.252.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.252.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.253.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.253.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.253.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.254.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.254.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.254.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.255.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.255.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.255.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.26.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.26.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.26.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.27.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.27.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.27.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.28.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.28.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.28.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.29.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.29.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.29.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.3.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.3.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.3.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.30.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.30.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.30.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.31.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.31.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.31.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.32.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.32.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.32.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.33.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.33.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.33.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.34.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.34.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.34.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.35.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.35.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.35.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.36.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.36.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.36.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.37.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.37.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.37.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.38.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.38.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.38.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.39.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.39.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.39.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.4.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.4.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.4.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.40.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.40.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.40.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.41.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.41.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.41.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.42.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.42.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.42.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.43.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.43.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.43.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.44.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.44.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.44.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.45.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.45.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.45.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.46.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.46.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.46.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.47.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.47.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.47.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.48.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.48.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.48.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.49.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.49.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.49.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.5.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.5.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.5.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.50.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.50.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.50.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.51.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.51.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.51.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.52.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.52.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.52.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.53.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.53.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.53.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.54.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.54.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.54.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.55.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.55.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.55.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.56.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.56.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.56.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.57.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.57.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.57.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.58.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.58.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.58.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.59.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.59.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.59.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.6.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.6.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.6.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.60.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.60.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.60.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.61.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.61.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.61.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.62.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.62.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.62.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.63.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.63.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.63.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.64.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.64.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.64.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.65.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.65.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.65.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.66.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.66.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.66.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.67.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.67.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.67.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.68.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.68.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.68.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.69.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.69.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.69.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.7.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.7.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.7.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.70.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.70.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.70.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.71.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.71.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.71.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.72.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.72.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.72.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.73.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.73.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.73.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.74.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.74.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.74.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.75.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.75.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.75.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.76.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.76.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.76.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.77.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.77.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.77.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.78.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.78.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.78.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.79.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.79.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.79.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.8.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.8.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.8.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.80.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.80.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.80.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.81.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.81.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.81.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.82.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.82.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.82.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.83.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.83.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.83.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.84.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.84.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.84.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.85.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.85.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.85.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.86.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.86.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.86.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.87.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.87.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.87.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.88.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.88.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.88.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.89.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.89.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.89.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.9.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.9.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.9.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.90.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.90.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.90.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.91.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.91.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.91.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.92.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.92.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.92.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.93.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.93.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.93.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.94.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.94.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.94.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.95.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.95.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.95.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.96.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.96.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.96.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.97.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.97.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.97.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.98.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.98.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.98.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.99.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.99.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.experts.99.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.12.mlp.gate.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.A_log": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.dt_bias": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.norm.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.0.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.0.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.0.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.1.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.1.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.1.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.10.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.10.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.10.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.100.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.100.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.100.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.101.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.101.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.101.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.102.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.102.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.102.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.103.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.103.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.103.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.104.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.104.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.104.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.105.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.105.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.105.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.106.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.106.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.106.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.107.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.107.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.107.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.108.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.108.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.108.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.109.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.109.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.109.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.11.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.11.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.11.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.110.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.110.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.110.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.111.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.111.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.111.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.112.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.112.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.112.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.113.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.113.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.113.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.114.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.114.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.114.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.115.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.115.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.115.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.116.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.116.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.116.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.117.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.117.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.117.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.118.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.118.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.118.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.119.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.119.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.119.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.12.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.12.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.12.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.120.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.120.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.120.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.121.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.121.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.121.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.122.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.122.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.122.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.123.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.123.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.123.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.124.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.124.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.124.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.125.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.125.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.125.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.126.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.126.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.126.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.127.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.127.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.127.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.128.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.128.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.128.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.129.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.129.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.129.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.13.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.13.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.13.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.130.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.130.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.130.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.131.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.131.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.131.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.132.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.132.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.132.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.133.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.133.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.133.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.134.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.134.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.134.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.135.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.135.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.135.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.136.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.136.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.136.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.137.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.137.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.137.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.138.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.138.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.138.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.139.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.139.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.139.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.14.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.14.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.14.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.140.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.140.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.140.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.141.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.141.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.141.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.142.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.142.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.142.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.143.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.143.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.143.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.144.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.144.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.144.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.145.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.145.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.145.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.146.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.146.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.146.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.147.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.147.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.147.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.148.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.148.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.148.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.149.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.149.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.149.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.15.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.15.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.15.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.150.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.150.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.150.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.151.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.151.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.151.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.152.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.152.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.152.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.153.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.153.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.153.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.154.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.154.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.154.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.155.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.155.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.155.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.156.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.156.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.156.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.157.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.157.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.157.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.158.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.158.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.158.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.159.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.159.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.159.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.16.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.16.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.16.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.160.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.160.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.160.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.161.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.161.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.161.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.162.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.162.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.162.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.163.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.163.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.163.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.164.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.164.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.164.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.165.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.165.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.165.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.166.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.166.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.166.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.167.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.167.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.167.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.168.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.168.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.168.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.169.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.169.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.169.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.17.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.17.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.17.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.170.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.170.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.170.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.171.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.171.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.171.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.172.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.172.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.172.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.173.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.173.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.173.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.174.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.174.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.174.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.175.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.175.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.175.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.176.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.176.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.176.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.177.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.177.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.177.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.178.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.178.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.178.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.179.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.179.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.179.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.18.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.18.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.18.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.180.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.180.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.180.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.181.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.181.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.181.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.182.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.182.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.182.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.183.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.183.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.183.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.184.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.184.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.184.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.185.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.185.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.185.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.186.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.186.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.186.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.187.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.187.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.187.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.188.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.188.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.188.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.189.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.189.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.189.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.19.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.19.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.19.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.190.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.190.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.190.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.191.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.191.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.191.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.192.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.192.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.192.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.193.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.193.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.193.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.194.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.194.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.194.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.195.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.195.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.195.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.196.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.196.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.196.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.197.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.197.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.197.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.198.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.198.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.198.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.199.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.199.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.199.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.2.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.2.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.2.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.20.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.20.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.20.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.200.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.200.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.200.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.201.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.201.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.201.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.202.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.202.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.202.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.203.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.203.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.203.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.204.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.204.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.204.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.205.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.205.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.205.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.206.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.206.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.206.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.207.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.207.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.207.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.208.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.208.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.208.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.209.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.209.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.209.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.21.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.21.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.21.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.210.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.210.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.210.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.211.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.211.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.211.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.212.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.212.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.212.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.213.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.213.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.213.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.214.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.214.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.214.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.215.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.215.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.215.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.216.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.216.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.216.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.217.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.217.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.217.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.218.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.218.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.218.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.219.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.219.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.219.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.22.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.22.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.22.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.220.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.220.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.220.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.221.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.221.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.221.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.222.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.222.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.222.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.223.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.223.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.223.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.224.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.224.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.224.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.225.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.225.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.225.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.226.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.226.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.226.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.227.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.227.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.227.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.228.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.228.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.228.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.229.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.229.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.229.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.23.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.23.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.23.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.230.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.230.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.230.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.231.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.231.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.231.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.232.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.232.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.232.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.233.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.233.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.233.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.234.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.234.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.234.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.235.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.235.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.235.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.236.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.236.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.236.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.237.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.237.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.237.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.238.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.238.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.238.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.239.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.239.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.239.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.24.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.24.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.24.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.240.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.240.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.240.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.241.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.241.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.241.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.242.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.242.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.242.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.243.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.243.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.243.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.244.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.244.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.244.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.245.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.245.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.245.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.246.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.246.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.246.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.247.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.247.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.247.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.248.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.248.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.248.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.249.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.249.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.249.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.25.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.25.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.25.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.250.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.250.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.250.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.251.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.251.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.251.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.252.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.252.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.252.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.253.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.253.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.253.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.254.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.254.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.254.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.255.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.255.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.255.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.26.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.26.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.26.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.27.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.27.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.27.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.28.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.28.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.28.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.29.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.29.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.29.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.3.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.3.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.3.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.30.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.30.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.30.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.31.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.31.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.31.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.32.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.32.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.32.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.33.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.33.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.33.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.34.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.34.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.34.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.35.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.35.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.35.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.36.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.36.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.36.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.37.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.37.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.37.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.38.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.38.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.38.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.39.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.39.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.39.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.4.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.4.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.4.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.40.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.40.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.40.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.41.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.41.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.41.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.42.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.42.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.42.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.43.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.43.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.43.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.44.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.44.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.44.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.45.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.45.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.45.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.46.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.46.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.46.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.47.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.47.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.47.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.48.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.48.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.48.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.49.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.49.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.49.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.5.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.5.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.5.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.50.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.50.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.50.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.51.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.51.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.51.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.52.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.52.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.52.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.53.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.53.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.53.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.54.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.54.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.54.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.55.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.55.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.55.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.56.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.56.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.56.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.57.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.57.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.57.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.58.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.58.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.58.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.59.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.59.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.59.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.6.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.6.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.6.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.60.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.60.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.60.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.61.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.61.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.61.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.62.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.62.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.62.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.63.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.63.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.63.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.64.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.64.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.64.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.65.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.65.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.65.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.66.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.66.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.66.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.67.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.67.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.67.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.68.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.68.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.68.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.69.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.69.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.69.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.7.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.7.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.7.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.70.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.70.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.70.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.71.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.71.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.71.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.72.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.72.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.72.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.73.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.73.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.73.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.74.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.74.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.74.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.75.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.75.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.75.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.76.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.76.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.76.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.77.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.77.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.77.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.78.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.78.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.78.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.79.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.79.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.79.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.8.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.8.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.8.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.80.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.80.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.80.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.81.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.81.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.81.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.82.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.82.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.82.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.83.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.83.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.83.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.84.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.84.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.84.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.85.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.85.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.85.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.86.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.86.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.86.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.87.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.87.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.87.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.88.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.88.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.88.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.89.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.89.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.89.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.9.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.9.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.9.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.90.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.90.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.90.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.91.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.91.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.91.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.92.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.92.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.92.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.93.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.93.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.93.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.94.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.94.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.94.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.95.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.95.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.95.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.96.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.96.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.96.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.97.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.97.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.97.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.98.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.98.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.98.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.99.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.99.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.experts.99.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.gate.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00011-of-00033.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.A_log": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.dt_bias": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.norm.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.0.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.0.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.0.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.1.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.1.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.1.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.10.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.10.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.10.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.100.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.100.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.100.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.101.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.101.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.101.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.102.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.102.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.102.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.103.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.103.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.103.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.104.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.104.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.104.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.105.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.105.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.105.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.106.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.106.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.106.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.107.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.107.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.107.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.108.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.108.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.108.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.109.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.109.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.109.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.11.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.11.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.11.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.110.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.110.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.110.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.111.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.111.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.111.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.112.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.112.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.112.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.113.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.113.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.113.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.114.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.114.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.114.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.115.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.115.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.115.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.116.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.116.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.116.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.117.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.117.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.117.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.118.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.118.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.118.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.119.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.119.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.119.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.12.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.12.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.12.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.120.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.120.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.120.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.121.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.121.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.121.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.122.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.122.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.122.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.123.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.123.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.123.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.124.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.124.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.124.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.125.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.125.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.125.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.126.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.126.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.126.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.127.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.127.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.127.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.128.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.128.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.128.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.129.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.129.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.129.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.13.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.13.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.13.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.130.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.130.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.130.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.131.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.131.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.131.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.132.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.132.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.132.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.133.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.133.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.133.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.134.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.134.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.134.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.135.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.135.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.135.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.136.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.136.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.136.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.137.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.137.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.137.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.138.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.138.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.138.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.139.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.139.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.139.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.14.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.14.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.14.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.140.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.140.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.140.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.141.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.141.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.141.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.142.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.142.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.142.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.143.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.143.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.143.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.144.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.144.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.144.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.145.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.145.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.145.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.146.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.146.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.146.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.147.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.147.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.147.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.148.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.148.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.148.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.149.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.149.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.149.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.15.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.15.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.15.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.150.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.150.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.150.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.151.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.151.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.151.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.152.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.152.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.152.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.153.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.153.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.153.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.154.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.154.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.154.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.155.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.155.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.155.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.156.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.156.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.156.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.157.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.157.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.157.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.158.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.158.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.158.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.159.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.159.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.159.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.16.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.16.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.16.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.160.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.160.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.160.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.161.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.161.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.161.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.162.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.162.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.162.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.163.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.163.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.163.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.164.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.164.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.164.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.165.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.165.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.165.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.166.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.166.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.166.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.167.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.167.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.167.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.168.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.168.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.168.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.169.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.169.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.169.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.17.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.17.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.17.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.170.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.170.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.170.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.171.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.171.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.171.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.172.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.172.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.172.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.173.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.173.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.173.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.174.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.174.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.174.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.175.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.175.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.175.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.176.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.176.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.176.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.177.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.177.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.177.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.178.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.178.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.178.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.179.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.179.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.179.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.18.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.18.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.18.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.180.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.180.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.180.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.181.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.181.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.181.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.182.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.182.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.182.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.183.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.183.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.183.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.184.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.184.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.184.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.185.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.185.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.185.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.186.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.186.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.186.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.187.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.187.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.187.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.188.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.188.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.188.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.189.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.189.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.189.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.19.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.19.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.19.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.190.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.190.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.190.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.191.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.191.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.191.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.192.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.192.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.192.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.193.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.193.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.193.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.194.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.194.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.194.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.195.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.195.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.195.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.196.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.196.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.196.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.197.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.197.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.197.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.198.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.198.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.198.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.199.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.199.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.199.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.2.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.2.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.2.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.20.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.20.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.20.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.200.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.200.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.200.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.201.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.201.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.201.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.202.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.202.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.202.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.203.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.203.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.203.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.204.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.204.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.204.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.205.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.205.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.205.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.206.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.206.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.206.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.207.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.207.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.207.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.208.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.208.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.208.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.209.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.209.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.209.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.21.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.21.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.21.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.210.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.210.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.210.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.211.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.211.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.211.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.212.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.212.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.212.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.213.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.213.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.213.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.214.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.214.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.214.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.215.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.215.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.215.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.216.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.216.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.216.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.217.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.217.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.217.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.218.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.218.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.218.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.219.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.219.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.219.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.22.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.22.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.22.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.220.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.220.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.220.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.221.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.221.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.221.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.222.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.222.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.222.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.223.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.223.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.223.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.224.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.224.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.224.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.225.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.225.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.225.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.226.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.226.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.226.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.227.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.227.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.227.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.228.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.228.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.228.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.229.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.229.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.229.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.23.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.23.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.23.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.230.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.230.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.230.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.231.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.231.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.231.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.232.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.232.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.232.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.233.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.233.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.233.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.234.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.234.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.234.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.235.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.235.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.235.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.236.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.236.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.236.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.237.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.237.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.237.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.238.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.238.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.238.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.239.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.239.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.239.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.24.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.24.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.24.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.240.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.240.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.240.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.241.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.241.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.241.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.242.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.242.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.242.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.243.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.243.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.243.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.244.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.244.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.244.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.245.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.245.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.245.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.246.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.246.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.246.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.247.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.247.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.247.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.248.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.248.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.248.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.249.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.249.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.249.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.25.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.25.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.25.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.250.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.250.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.250.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.251.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.251.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.251.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.252.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.252.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.252.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.253.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.253.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.253.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.254.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.254.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.254.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.255.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.255.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.255.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.26.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.26.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.26.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.27.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.27.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.27.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.28.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.28.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.28.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.29.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.29.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.29.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.3.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.3.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.3.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.30.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.30.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.30.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.31.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.31.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.31.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.32.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.32.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.32.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.33.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.33.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.33.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.34.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.34.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.34.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.35.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.35.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.35.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.36.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.36.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.36.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.37.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.37.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.37.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.38.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.38.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.38.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.39.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.39.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.39.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.4.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.4.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.4.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.40.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.40.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.40.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.41.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.41.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.41.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.42.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.42.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.42.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.43.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.43.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.43.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.44.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.44.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.44.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.45.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.45.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.45.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.46.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.46.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.46.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.47.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.47.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.47.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.48.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.48.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.48.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.49.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.49.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.49.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.5.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.5.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.5.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.50.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.50.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.50.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.51.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.51.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.51.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.52.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.52.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.52.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.53.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.53.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.53.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.54.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.54.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.54.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.55.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.55.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.55.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.56.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.56.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.56.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.57.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.57.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.57.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.58.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.58.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.58.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.59.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.59.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.59.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.6.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.6.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.6.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.60.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.60.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.60.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.61.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.61.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.61.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.62.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.62.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.62.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.63.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.63.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.63.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.64.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.64.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.64.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.65.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.65.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.65.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.66.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.66.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.66.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.67.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.67.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.67.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.68.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.68.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.68.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.69.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.69.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.69.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.7.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.7.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.7.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.70.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.70.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.70.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.71.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.71.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.71.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.72.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.72.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.72.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.73.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.73.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.73.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.74.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.74.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.74.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.75.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.75.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.75.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.76.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.76.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.76.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.77.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.77.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.77.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.78.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.78.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.78.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.79.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.79.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.79.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.8.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.8.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.8.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.80.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.80.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.80.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.81.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.81.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.81.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.82.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.82.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.82.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.83.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.83.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.83.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.84.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.84.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.84.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.85.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.85.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.85.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.86.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.86.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.86.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.87.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.87.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.87.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.88.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.88.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.88.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.89.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.89.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.89.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.9.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.9.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.9.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.90.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.90.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.90.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.91.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.91.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.91.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.92.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.92.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.92.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.93.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.93.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.93.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.94.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.94.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.94.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.95.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.95.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.95.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.96.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.96.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.96.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.97.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.97.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.97.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.98.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.98.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.98.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.99.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.99.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.experts.99.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.gate.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.0.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.0.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.0.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.1.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.1.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.1.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.10.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.10.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.10.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.100.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.100.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.100.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.101.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.101.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.101.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.102.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.102.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.102.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.103.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.103.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.103.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.104.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.104.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.104.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.105.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.105.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.105.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.106.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.106.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.106.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.107.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.107.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.107.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.108.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.108.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.108.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.109.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.109.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.109.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.11.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.11.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.11.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.110.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.110.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.110.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.111.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.111.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.111.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.112.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.112.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.112.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.113.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.113.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.113.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.114.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.114.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.114.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.115.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.115.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.115.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.116.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.116.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.116.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.117.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.117.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.117.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.118.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.118.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.118.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.119.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.119.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.119.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.12.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.12.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.12.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.120.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.120.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.120.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.121.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.121.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.121.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.122.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.122.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.122.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.123.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.123.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.123.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.124.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.124.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.124.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.125.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.125.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.125.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.126.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.126.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.126.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.127.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.127.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.127.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.128.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.128.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.128.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.129.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.129.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.129.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.13.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.13.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.13.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.130.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.130.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.130.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.131.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.131.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.131.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.132.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.132.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.132.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.133.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.133.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.133.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.134.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.134.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.134.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.135.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.135.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.135.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.136.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.136.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.136.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.137.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.137.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.137.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.138.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.138.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.138.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.139.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.139.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.139.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.14.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.14.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.14.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.140.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.140.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.140.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.141.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.141.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.141.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.142.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.142.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.142.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.143.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.143.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.143.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.144.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.144.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.144.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.145.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.145.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.145.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.146.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.146.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.146.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.147.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.147.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.147.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.148.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.148.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.148.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.149.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.149.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.149.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.15.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.15.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.15.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.150.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.150.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.150.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.151.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.151.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.151.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.152.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.152.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.152.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.153.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.153.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.153.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.154.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.154.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.154.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.155.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.155.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.155.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.156.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.156.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.156.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.157.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.157.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.157.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.158.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.158.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.158.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.159.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.159.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.159.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.16.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.16.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.16.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.160.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.160.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.160.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.161.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.161.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.161.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.162.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.162.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.162.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.163.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.163.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.163.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.164.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.164.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.164.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.165.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.165.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.165.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.166.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.166.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.166.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.167.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.167.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.167.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.168.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.168.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.168.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.169.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.169.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.169.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.17.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.17.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.17.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.170.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.170.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.170.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.171.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.171.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.171.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.172.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.172.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.172.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.173.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.173.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.173.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.174.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.174.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.174.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.175.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.175.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.175.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.176.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.176.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.176.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.177.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.177.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.177.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.178.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.178.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.178.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.179.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.179.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.179.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.18.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.18.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.18.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.180.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.180.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.180.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.181.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.181.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.181.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.182.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.182.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.182.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.183.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.183.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.183.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.184.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.184.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.184.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.185.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.185.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.185.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.186.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.186.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.186.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.187.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.187.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.187.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.188.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.188.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.188.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.189.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.189.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.189.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.19.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.19.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.19.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.190.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.190.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.190.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.191.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.191.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.191.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.192.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.192.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.192.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.193.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.193.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.193.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.194.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.194.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.194.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.195.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.195.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.195.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.196.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.196.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.196.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.197.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.197.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.197.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.198.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.198.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.198.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.199.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.199.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.199.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.2.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.2.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.2.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.20.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.20.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.20.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.200.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.200.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.200.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.201.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.201.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.201.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.202.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.202.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.202.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.203.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.203.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.203.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.204.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.204.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.204.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.205.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.205.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.205.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.206.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.206.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.206.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.207.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.207.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.207.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.208.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.208.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.208.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.209.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.209.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.209.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.21.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.21.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.21.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.210.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.210.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.210.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.211.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.211.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.211.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.212.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.212.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.212.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.213.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.213.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.213.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.214.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.214.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.214.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.215.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.215.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.215.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.216.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.216.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.216.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.217.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.217.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.217.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.218.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.218.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.218.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.219.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.219.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.219.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.22.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.22.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.22.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.220.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.220.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.220.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.221.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.221.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.221.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.222.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.222.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.222.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.223.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.223.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.223.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.224.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.224.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.224.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.225.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.225.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.225.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.226.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.226.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.226.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.227.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.227.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.227.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.228.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.228.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.228.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.229.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.229.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.229.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.23.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.23.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.23.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.230.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.230.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.230.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.231.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.231.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.231.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.232.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.232.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.232.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.233.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.233.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.233.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.234.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.234.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.234.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.235.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.235.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.235.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.236.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.236.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.236.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.237.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.237.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.237.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.238.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.238.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.238.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.239.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.239.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.239.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.24.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.24.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.24.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.240.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.240.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.240.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.241.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.241.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.241.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.242.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.242.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.242.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.243.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.243.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.243.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.244.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.244.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.244.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.245.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.245.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.245.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.246.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.246.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.246.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.247.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.247.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.247.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.248.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.248.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.248.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.249.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.249.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.249.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.25.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.25.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.25.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.250.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.250.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.250.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.251.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.251.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.251.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.252.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.252.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.252.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.253.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.253.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.253.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.254.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.254.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.254.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.255.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.255.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.255.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.26.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.26.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.26.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.27.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.27.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.27.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.28.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.28.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.28.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.29.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.29.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.29.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.3.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.3.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.3.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.30.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.30.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.30.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.31.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.31.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.31.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.32.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.32.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.32.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.33.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.33.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.33.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.34.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.34.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.34.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.35.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.35.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.35.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.36.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.36.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.36.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.37.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.37.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.37.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.38.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.38.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.38.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.39.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.39.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.39.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.4.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.4.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.4.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.40.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.40.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.40.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.41.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.41.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.41.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.42.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.42.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.42.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.43.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.43.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.43.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.44.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.44.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.44.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.45.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.45.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.45.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.46.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.46.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.46.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.47.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.47.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.47.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.48.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.48.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.48.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.49.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.49.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.49.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.5.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.5.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.5.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.50.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.50.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.50.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.51.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.51.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.51.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.52.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.52.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.52.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.53.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.53.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.53.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.54.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.54.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.54.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.55.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.55.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.55.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.56.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.56.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.56.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.57.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.57.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.57.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.58.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.58.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.58.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.59.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.59.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.59.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.6.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.6.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.6.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.60.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.60.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.60.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.61.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.61.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.61.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.62.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.62.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.62.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.63.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.63.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.63.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.64.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.64.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.64.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.65.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.65.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.65.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.66.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.66.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.66.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.67.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.67.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.67.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.68.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.68.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.68.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.69.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.69.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.69.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.7.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.7.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.7.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.70.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.70.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.70.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.71.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.71.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.71.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.72.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.72.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.72.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.73.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.73.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.73.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.74.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.74.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.74.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.75.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.75.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.75.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.76.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.76.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.76.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.77.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.77.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.77.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.78.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.78.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.78.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.79.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.79.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.79.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.8.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.8.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.8.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.80.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.80.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.80.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.81.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.81.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.81.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.82.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.82.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.82.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.83.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.83.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.83.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.84.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.84.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.84.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.85.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.85.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.85.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.86.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.86.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.86.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.87.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.87.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.87.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.88.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.88.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.88.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.89.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.89.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.89.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.9.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.9.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.9.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.90.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.90.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.90.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.91.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.91.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.91.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.92.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.92.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.92.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.93.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.93.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.93.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.94.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.94.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.94.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.95.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.95.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.95.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.96.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.96.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.96.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.97.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.97.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.97.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.98.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.98.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.98.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.99.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.99.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.experts.99.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.gate.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00013-of-00033.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.A_log": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.dt_bias": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.norm.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.0.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.0.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.0.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.1.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.1.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.1.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.10.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.10.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.10.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.100.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.100.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.100.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.101.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.101.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.101.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.102.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.102.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.102.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.103.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.103.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.103.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.104.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.104.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.104.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.105.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.105.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.105.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.106.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.106.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.106.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.107.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.107.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.107.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.108.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.108.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.108.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.109.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.109.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.109.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.11.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.11.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.11.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.110.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.110.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.110.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.111.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.111.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.111.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.112.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.112.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.112.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.113.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.113.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.113.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.114.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.114.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.114.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.115.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.115.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.115.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.116.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.116.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.116.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.117.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.117.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.117.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.118.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.118.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.118.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.119.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.119.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.119.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.12.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.12.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.12.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.120.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.120.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.120.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.121.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.121.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.121.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.122.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.122.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.122.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.123.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.123.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.123.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.124.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.124.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.124.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.125.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.125.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.125.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.126.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.126.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.126.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.127.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.127.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.127.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.128.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.128.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.128.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.129.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.129.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.129.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.13.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.13.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.13.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.130.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.130.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.130.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.131.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.131.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.131.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.132.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.132.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.132.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.133.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.133.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.133.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.134.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.134.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.134.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.135.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.135.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.135.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.136.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.136.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.136.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.137.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.137.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.137.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.138.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.138.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.138.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.139.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.139.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.139.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.14.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.14.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.14.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.140.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.140.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.140.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.141.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.141.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.141.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.142.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.142.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.142.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.143.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.143.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.143.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.144.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.144.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.144.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.145.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.145.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.145.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.146.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.146.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.146.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.147.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.147.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.147.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.148.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.148.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.148.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.149.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.149.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.149.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.15.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.15.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.15.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.150.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.150.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.150.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.151.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.151.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.151.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.152.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.152.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.152.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.153.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.153.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.153.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.154.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.154.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.154.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.155.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.155.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.155.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.156.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.156.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.156.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.157.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.157.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.157.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.158.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.158.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.158.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.159.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.159.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.159.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.16.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.16.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.16.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.160.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.160.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.160.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.161.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.161.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.161.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.162.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.162.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.162.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.163.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.163.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.163.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.164.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.164.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.164.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.165.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.165.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.165.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.166.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.166.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.166.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.167.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.167.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.167.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.168.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.168.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.168.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.169.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.169.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.169.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.17.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.17.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.17.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.170.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.170.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.170.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.171.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.171.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.171.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.172.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.172.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.172.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.173.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.173.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.173.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.174.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.174.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.174.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.175.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.175.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.175.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.176.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.176.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.176.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.177.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.177.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.177.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.178.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.178.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.178.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.179.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.179.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.179.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.18.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.18.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.18.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.180.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.180.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.180.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.181.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.181.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.181.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.182.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.182.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.182.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.183.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.183.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.183.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.184.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.184.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.184.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.185.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.185.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.185.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.186.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.186.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.186.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.187.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.187.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.187.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.188.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.188.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.188.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.189.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.189.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.189.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.19.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.19.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.19.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.190.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.190.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.190.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.191.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.191.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.191.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.192.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.192.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.192.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.193.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.193.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.193.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.194.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.194.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.194.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.195.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.195.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.195.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.196.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.196.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.196.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.197.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.197.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.197.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.198.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.198.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.198.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.199.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.199.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.199.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.2.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.2.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.2.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.20.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.20.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.20.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.200.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.200.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.200.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.201.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.201.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.201.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.202.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.202.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.202.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.203.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.203.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.203.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.204.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.204.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.204.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.205.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.205.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.205.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.206.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.206.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.206.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.207.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.207.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.207.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.208.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.208.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.208.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.209.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.209.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.209.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.21.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.21.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.21.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.210.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.210.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.210.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.211.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.211.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.211.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.212.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.212.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.212.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.213.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.213.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.213.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.214.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.214.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.214.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.215.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.215.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.215.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.216.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.216.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.216.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.217.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.217.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.217.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.218.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.218.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.218.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.219.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.219.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.219.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.22.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.22.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.22.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.220.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.220.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.220.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.221.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.221.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.221.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.222.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.222.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.222.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.223.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.223.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.223.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.224.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.224.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.224.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.225.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.225.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.225.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.226.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.226.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.226.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.227.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.227.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.227.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.228.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.228.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.228.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.229.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.229.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.229.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.23.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.23.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.23.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.230.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.230.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.230.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.231.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.231.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.231.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.232.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.232.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.232.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.233.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.233.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.233.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.234.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.234.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.234.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.235.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.235.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.235.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.236.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.236.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.236.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.237.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.237.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.237.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.238.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.238.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.238.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.239.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.239.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.239.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.24.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.24.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.24.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.240.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.240.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.240.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.241.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.241.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.241.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.242.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.242.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.242.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.243.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.243.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.243.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.244.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.244.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.244.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.245.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.245.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.245.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.246.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.246.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.246.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.247.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.247.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.247.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.248.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.248.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.248.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.249.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.249.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.249.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.25.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.25.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.25.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.250.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.250.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.250.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.251.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.251.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.251.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.252.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.252.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.252.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.253.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.253.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.253.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.254.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.254.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.254.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.255.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.255.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.255.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.26.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.26.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.26.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.27.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.27.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.27.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.28.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.28.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.28.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.29.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.29.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.29.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.3.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.3.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.3.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.30.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.30.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.30.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.31.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.31.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.31.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.32.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.32.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.32.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.33.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.33.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.33.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.34.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.34.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.34.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.35.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.35.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.35.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.36.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.36.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.36.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.37.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.37.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.37.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.38.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.38.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.38.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.39.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.39.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.39.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.4.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.4.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.4.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.40.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.40.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.40.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.41.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.41.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.41.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.42.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.42.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.42.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.43.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.43.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.43.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.44.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.44.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.44.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.45.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.45.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.45.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.46.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.46.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.46.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.47.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.47.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.47.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.48.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.48.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.48.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.49.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.49.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.49.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.5.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.5.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.5.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.50.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.50.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.50.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.51.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.51.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.51.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.52.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.52.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.52.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.53.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.53.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.53.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.54.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.54.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.54.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.55.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.55.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.55.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.56.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.56.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.56.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.57.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.57.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.57.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.58.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.58.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.58.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.59.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.59.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.59.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.6.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.6.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.6.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.60.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.60.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.60.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.61.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.61.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.61.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.62.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.62.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.62.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.63.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.63.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.63.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.64.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.64.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.64.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.65.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.65.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.65.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.66.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.66.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.66.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.67.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.67.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.67.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.68.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.68.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.68.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.69.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.69.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.69.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.7.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.7.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.7.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.70.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.70.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.70.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.71.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.71.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.71.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.72.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.72.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.72.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.73.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.73.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.73.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.74.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.74.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.74.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.75.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.75.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.75.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.76.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.76.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.76.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.77.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.77.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.77.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.78.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.78.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.78.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.79.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.79.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.79.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.8.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.8.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.8.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.80.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.80.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.80.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.81.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.81.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.81.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.82.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.82.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.82.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.83.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.83.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.83.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.84.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.84.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.84.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.85.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.85.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.85.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.86.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.86.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.86.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.87.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.87.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.87.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.88.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.88.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.88.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.89.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.89.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.89.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.9.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.9.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.9.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.90.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.90.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.90.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.91.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.91.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.91.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.92.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.92.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.92.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.93.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.93.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.93.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.94.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.94.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.94.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.95.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.95.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.95.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.96.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.96.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.96.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.97.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.97.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.97.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.98.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.98.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.98.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.99.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.99.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.experts.99.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.gate.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.A_log": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.dt_bias": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.norm.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.0.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.0.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.0.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.1.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.1.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.1.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.10.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.10.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.10.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.100.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.100.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.100.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.101.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.101.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.101.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.102.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.102.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.102.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.103.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.103.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.103.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.104.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.104.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.104.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.105.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.105.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.105.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.106.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.106.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.106.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.107.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.107.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.107.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.108.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.108.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.108.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.109.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.109.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.109.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.11.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.11.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.11.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.110.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.110.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.110.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.111.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.111.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.111.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.112.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.112.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.112.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.113.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.113.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.113.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.114.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.114.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.114.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.115.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.115.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.115.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.116.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.116.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.116.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.117.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.117.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.117.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.118.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.118.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.118.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.119.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.119.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.119.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.12.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.12.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.12.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.120.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.120.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.120.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.121.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.121.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.121.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.122.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.122.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.122.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.123.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.123.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.123.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.124.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.124.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.124.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.125.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.125.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.125.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.126.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.126.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.126.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.127.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.127.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.127.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.128.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.128.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.128.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.129.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.129.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.129.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.13.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.13.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.13.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.130.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.130.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.130.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.131.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.131.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.131.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.132.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.132.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.132.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.133.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.133.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.133.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.134.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.134.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.134.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.135.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.135.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.135.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.136.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.136.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.136.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.137.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.137.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.137.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.138.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.138.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.138.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.139.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.139.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.139.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.14.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.14.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.14.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.140.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.140.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.140.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.141.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.141.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.141.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.142.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.142.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.142.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.143.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.143.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.143.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.144.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.144.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.144.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.145.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.145.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.145.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.146.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.146.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.146.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.147.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.147.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.147.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.148.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.148.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.148.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.149.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.149.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.149.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.15.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.15.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.15.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.150.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.150.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.150.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.151.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.151.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.151.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.152.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.152.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.152.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.153.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.153.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.153.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.154.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.154.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.154.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.155.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.155.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.155.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.156.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.156.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.156.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.157.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.157.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.157.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.158.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.158.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.158.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.159.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.159.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.159.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.16.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.16.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.16.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.160.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.160.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.160.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.161.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.161.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.161.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.162.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.162.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.162.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.163.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.163.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.163.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.164.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.164.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.164.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.165.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.165.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.165.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.166.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.166.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.166.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.167.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.167.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.167.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.168.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.168.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.168.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.169.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.169.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.169.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.17.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.17.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.17.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.170.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.170.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.170.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.171.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.171.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.171.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.172.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.172.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.172.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.173.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.173.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.173.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.174.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.174.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.174.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.175.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.175.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.175.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.176.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.176.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.176.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.177.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.177.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.177.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.178.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.178.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.178.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.179.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.179.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.179.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.18.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.18.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.18.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.180.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.180.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.180.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.181.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.181.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.181.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.182.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.182.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.182.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.183.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.183.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.183.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.184.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.184.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.184.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.185.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.185.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.185.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.186.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.186.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.186.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.187.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.187.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.187.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.188.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.188.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.188.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.189.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.189.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.189.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.19.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.19.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.19.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.190.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.190.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.190.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.191.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.191.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.191.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.192.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.192.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.192.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.193.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.193.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.193.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.194.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.194.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.194.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.195.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.195.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.195.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.196.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.196.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.196.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.197.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.197.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.197.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.198.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.198.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.198.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.199.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.199.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.199.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.2.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.2.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.2.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.20.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.20.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.20.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.200.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.200.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.200.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.201.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.201.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.201.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.202.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.202.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.202.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.203.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.203.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.203.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.204.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.204.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.204.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.205.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.205.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.205.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.206.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.206.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.206.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.207.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.207.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.207.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.208.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.208.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.208.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.209.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.209.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.209.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.21.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.21.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.21.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.210.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.210.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.210.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.211.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.211.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.211.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.212.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.212.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.212.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.213.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.213.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.213.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.214.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.214.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.214.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.215.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.215.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.215.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.216.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.216.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.216.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.217.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.217.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.217.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.218.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.218.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.218.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.219.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.219.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.219.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.22.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.22.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.22.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.220.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.220.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.220.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.221.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.221.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.221.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.222.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.222.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.222.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.223.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.223.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.223.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.224.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.224.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.224.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.225.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.225.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.225.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.226.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.226.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.226.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.227.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.227.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.227.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.228.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.228.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.228.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.229.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.229.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.229.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.23.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.23.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.23.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.230.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.230.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.230.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.231.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.231.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.231.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.232.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.232.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.232.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.233.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.233.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.233.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.234.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.234.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.234.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.235.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.235.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.235.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.236.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.236.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.236.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.237.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.237.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.237.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.238.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.238.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.238.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.239.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.239.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.239.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.24.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.24.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.24.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.240.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.240.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.240.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.241.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.241.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.241.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.242.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.242.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.242.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.243.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.243.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.243.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.244.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.244.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.244.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.245.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.245.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.245.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.246.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.246.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.246.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.247.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.247.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.247.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.248.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.248.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.248.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.249.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.249.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.249.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.25.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.25.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.25.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.250.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.250.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.250.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.251.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.251.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.251.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.252.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.252.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.252.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.253.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.253.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.253.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.254.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.254.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.254.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.255.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.255.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.255.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.26.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.26.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.26.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.27.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.27.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.27.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.28.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.28.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.28.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.29.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.29.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.29.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.3.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.3.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.3.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.30.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.30.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.30.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.31.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.31.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.31.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.32.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.32.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.32.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.33.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.33.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.33.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.34.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.34.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.34.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.35.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.35.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.35.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.36.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.36.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.36.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.37.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.37.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.37.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.38.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.38.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.38.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.39.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.39.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.39.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.4.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.4.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.4.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.40.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.40.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.40.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.41.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.41.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.41.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.42.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.42.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.42.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.43.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.43.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.43.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.44.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.44.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.44.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.45.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.45.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.45.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.46.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.46.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.46.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.47.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.47.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.47.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.48.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.48.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.48.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.49.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.49.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.49.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.5.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.5.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.5.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.50.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.50.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.50.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.51.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.51.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.51.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.52.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.52.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.52.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.53.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.53.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.53.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.54.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.54.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.54.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.55.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.55.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.55.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.56.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.56.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.56.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.57.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.57.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.57.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.58.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.58.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.58.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.59.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.59.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.59.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.6.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.6.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.6.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.60.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.60.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.60.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.61.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.61.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.61.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.62.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.62.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.62.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.63.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.63.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.63.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.64.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.64.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.64.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.65.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.65.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.65.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.66.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.66.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.66.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.67.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.67.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.67.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.68.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.68.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.68.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.69.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.69.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.69.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.7.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.7.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.7.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.70.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.70.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.70.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.71.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.71.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.71.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.72.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.72.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.72.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.73.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.73.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.73.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.74.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.74.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.74.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.75.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.75.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.75.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.76.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.76.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.76.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.77.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.77.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.77.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.78.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.78.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.78.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.79.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.79.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.79.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.8.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.8.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.8.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.80.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.80.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.80.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.81.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.81.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.81.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.82.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.82.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.82.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.83.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.83.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.83.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.84.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.84.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.84.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.85.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.85.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.85.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.86.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.86.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.86.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.87.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.87.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.87.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.88.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.88.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.88.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.89.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.89.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.89.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.9.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.9.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.9.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.90.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.90.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.90.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.91.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.91.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.91.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.92.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.92.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.92.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.93.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.93.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.93.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.94.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.94.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.94.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.95.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.95.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.95.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.96.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.96.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.96.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.97.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.97.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.97.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.98.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.98.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.98.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.99.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.99.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.experts.99.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.17.mlp.gate.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.A_log": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.dt_bias": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.norm.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.0.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.0.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.0.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.1.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.1.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.1.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.10.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.10.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.10.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.100.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.100.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.100.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.101.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.101.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.101.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.102.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.102.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.102.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.103.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.103.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.103.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.104.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.104.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.104.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.105.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.105.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.105.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.106.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.106.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.106.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.107.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.107.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.107.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.108.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.108.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.108.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.109.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.109.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.109.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.11.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.11.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.11.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.110.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.110.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.110.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.111.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.111.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.111.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.112.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.112.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.112.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.113.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.113.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.113.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.114.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.114.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.114.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.115.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.115.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.115.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.116.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.116.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.116.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.117.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.117.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.117.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.118.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.118.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.118.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.119.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.119.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.119.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.12.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.12.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.12.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.120.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.120.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.120.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.121.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.121.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.121.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.122.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.122.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.122.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.123.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.123.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.123.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.124.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.124.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.124.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.125.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.125.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.125.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.126.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.126.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.126.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.127.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.127.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.127.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.128.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.128.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.128.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.129.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.129.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.129.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.13.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.13.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.13.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.130.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.130.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.130.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.131.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.131.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.131.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.132.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.132.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.132.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.133.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.133.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.133.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.134.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.134.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.134.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.135.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.135.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.135.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.136.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.136.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.136.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.137.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.137.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.137.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.138.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.138.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.138.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.139.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.139.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.139.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.14.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.14.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.14.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.140.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.140.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.140.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.141.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.141.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.141.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.142.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.142.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.142.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.143.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.143.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.143.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.144.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.144.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.144.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.145.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.145.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.145.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.146.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.146.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.146.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.147.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.147.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.147.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.148.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.148.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.148.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.149.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.149.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.149.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.15.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.15.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.15.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.150.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.150.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.150.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.151.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.151.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.151.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.152.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.152.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.152.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.153.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.153.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.153.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.154.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.154.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.154.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.155.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.155.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.155.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.156.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.156.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.156.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.157.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.157.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.157.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.158.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.158.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.158.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.159.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.159.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.159.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.16.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.16.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.16.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.160.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.160.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.160.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.161.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.161.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.161.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.162.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.162.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.162.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.163.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.163.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.163.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.164.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.164.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.164.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.165.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.165.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.165.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.166.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.166.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.166.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.167.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.167.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.167.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.168.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.168.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.168.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.169.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.169.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.169.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.17.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.17.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.17.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.170.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.170.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.170.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.171.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.171.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.171.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.172.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.172.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.172.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.173.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.173.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.173.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.174.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.174.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.174.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.175.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.175.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.175.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.176.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.176.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.176.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.177.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.177.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.177.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.178.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.178.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.178.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.179.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.179.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.179.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.18.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.18.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.18.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.180.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.180.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.180.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.181.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.181.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.181.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.182.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.182.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.182.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.183.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.183.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.183.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.184.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.184.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.184.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.185.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.185.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.185.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.186.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.186.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.186.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.187.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.187.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.187.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.188.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.188.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.188.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.189.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.189.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.189.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.19.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.19.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.19.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.190.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.190.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.190.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.191.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.191.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.191.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.192.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.192.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.192.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.193.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.193.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.193.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.194.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.194.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.194.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.195.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.195.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.195.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.196.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.196.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.196.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.197.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.197.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.197.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.198.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.198.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.198.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.199.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.199.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.199.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.2.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.2.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.2.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.20.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.20.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.20.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.200.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.200.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.200.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.201.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.201.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.201.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.202.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.202.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.202.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.203.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.203.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.203.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.204.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.204.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.204.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.205.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.205.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.205.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.206.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.206.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.206.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.207.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.207.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.207.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.208.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.208.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.208.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.209.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.209.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.209.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.21.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.21.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.21.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.210.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.210.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.210.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.211.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.211.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.211.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.212.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.212.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.212.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.213.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.213.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.213.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.214.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.214.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.214.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.215.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.215.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.215.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.216.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.216.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.216.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.217.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.217.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.217.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.218.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.218.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.218.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.219.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.219.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.219.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.22.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.22.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.22.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.220.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.220.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.220.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.221.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.221.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.221.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.222.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.222.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.222.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.223.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.223.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.223.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.224.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.224.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.224.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.225.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.225.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.225.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.226.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.226.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.226.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.227.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.227.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.227.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.228.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.228.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.228.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.229.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.229.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.229.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.23.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.23.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.23.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.230.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.230.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.230.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.231.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.231.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.231.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.232.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.232.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.232.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.233.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.233.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.233.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.234.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.234.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.234.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.235.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.235.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.235.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.236.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.236.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.236.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.237.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.237.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.237.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.238.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.238.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.238.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.239.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.239.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.239.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.24.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.24.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.24.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.240.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.240.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.240.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.241.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.241.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.241.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.242.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.242.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.242.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.243.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.243.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.243.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.244.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.244.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.244.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.245.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.245.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.245.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.246.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.246.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.246.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.247.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.247.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.247.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.248.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.248.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.248.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.249.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.249.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.249.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.25.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.25.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.25.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.250.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.250.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.250.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.251.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.251.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.251.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.252.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.252.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.252.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.253.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.253.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.253.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.254.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.254.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.254.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.255.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.255.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.255.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.26.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.26.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.26.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.27.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.27.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.27.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.28.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.28.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.28.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.29.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.29.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.29.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.3.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.3.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.3.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.30.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.30.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.30.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.31.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.31.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.31.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.32.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.32.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.32.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.33.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.33.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.33.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.34.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.34.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.34.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.35.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.35.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.35.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.36.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.36.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.36.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.37.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.37.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.37.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.38.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.38.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.38.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.39.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.39.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.39.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.4.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.4.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.4.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.40.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.40.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.40.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.41.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.41.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.41.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.42.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.42.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.42.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.43.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.43.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.43.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.44.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.44.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.44.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.45.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.45.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.45.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.46.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.46.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.46.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.47.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.47.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.47.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.48.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.48.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.48.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.49.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.49.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.49.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.5.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.5.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.5.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.50.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.50.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.50.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.51.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.51.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.51.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.52.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.52.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.52.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.53.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.53.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.53.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.54.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.54.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.54.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.55.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.55.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.55.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.56.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.56.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.56.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.57.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.57.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.57.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.58.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.58.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.58.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.59.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.59.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.59.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.6.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.6.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.6.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.60.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.60.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.60.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.61.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.61.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.61.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.62.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.62.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.62.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.63.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.63.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.63.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.64.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.64.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.64.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.65.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.65.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.65.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.66.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.66.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.66.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.67.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.67.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.67.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.68.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.68.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.68.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.69.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.69.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.69.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.7.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.7.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.7.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.70.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.70.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.70.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.71.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.71.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.71.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.72.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.72.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.72.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.73.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.73.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.73.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.74.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.74.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.74.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.75.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.75.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.75.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.76.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.76.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.76.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.77.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.77.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.77.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.78.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.78.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.78.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.79.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.79.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.79.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.8.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.8.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.8.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.80.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.80.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.80.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.81.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.81.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.81.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.82.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.82.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.82.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.83.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.83.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.83.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.84.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.84.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.84.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.85.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.85.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.85.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.86.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.86.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.86.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.87.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.87.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.87.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.88.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.88.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.88.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.89.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.89.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.89.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.9.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.9.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.9.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.90.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.90.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.90.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.91.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.91.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.91.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.92.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.92.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.92.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.93.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.93.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.93.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.94.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.94.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.94.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.95.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.95.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.95.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.96.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.96.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.96.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.97.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.97.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.97.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.98.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.98.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.98.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.99.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.99.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.experts.99.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.gate.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00015-of-00033.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.0.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.0.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.0.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.1.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.1.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.1.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.10.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.10.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.10.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.100.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.100.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.100.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.101.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.101.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.101.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.102.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.102.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.102.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.103.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.103.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.103.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.104.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.104.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.104.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.105.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.105.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.105.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.106.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.106.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.106.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.107.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.107.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.107.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.108.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.108.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.108.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.109.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.109.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.109.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.11.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.11.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.11.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.110.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.110.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.110.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.111.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.111.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.111.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.112.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.112.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.112.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.113.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.113.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.113.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.114.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.114.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.114.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.115.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.115.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.115.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.116.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.116.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.116.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.117.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.117.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.117.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.118.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.118.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.118.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.119.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.119.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.119.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.12.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.12.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.12.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.120.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.120.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.120.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.121.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.121.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.121.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.122.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.122.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.122.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.123.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.123.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.123.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.124.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.124.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.124.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.125.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.125.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.125.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.126.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.126.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.126.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.127.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.127.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.127.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.128.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.128.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.128.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.129.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.129.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.129.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.13.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.13.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.13.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.130.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.130.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.130.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.131.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.131.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.131.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.132.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.132.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.132.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.133.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.133.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.133.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.134.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.134.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.134.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.135.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.135.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.135.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.136.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.136.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.136.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.137.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.137.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.137.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.138.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.138.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.138.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.139.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.139.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.139.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.14.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.14.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.14.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.140.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.140.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.140.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.141.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.141.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.141.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.142.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.142.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.142.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.143.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.143.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.143.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.144.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.144.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.144.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.145.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.145.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.145.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.146.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.146.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.146.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.147.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.147.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.147.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.148.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.148.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.148.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.149.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.149.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.149.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.15.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.15.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.15.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.150.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.150.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.150.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.151.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.151.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.151.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.152.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.152.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.152.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.153.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.153.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.153.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.154.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.154.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.154.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.155.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.155.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.155.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.156.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.156.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.156.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.157.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.157.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.157.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.158.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.158.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.158.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.159.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.159.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.159.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.16.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.16.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.16.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.160.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.160.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.160.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.161.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.161.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.161.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.162.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.162.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.162.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.163.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.163.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.163.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.164.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.164.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.164.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.165.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.165.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.165.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.166.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.166.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.166.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.167.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.167.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.167.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.168.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.168.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.168.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.169.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.169.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.169.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.17.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.17.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.17.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.170.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.170.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.170.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.171.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.171.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.171.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.172.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.172.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.172.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.173.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.173.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.173.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.174.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.174.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.174.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.175.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.175.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.175.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.176.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.176.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.176.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.177.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.177.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.177.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.178.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.178.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.178.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.179.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.179.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.179.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.18.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.18.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.18.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.180.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.180.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.180.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.181.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.181.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.181.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.182.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.182.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.182.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.183.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.183.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.183.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.184.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.184.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.184.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.185.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.185.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.185.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.186.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.186.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.186.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.187.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.187.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.187.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.188.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.188.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.188.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.189.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.189.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.189.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.19.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.19.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.19.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.190.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.190.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.190.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.191.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.191.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.191.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.192.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.192.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.192.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.193.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.193.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.193.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.194.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.194.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.194.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.195.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.195.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.195.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.196.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.196.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.196.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.197.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.197.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.197.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.198.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.198.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.198.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.199.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.199.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.199.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.2.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.2.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.2.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.20.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.20.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.20.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.200.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.200.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.200.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.201.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.201.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.201.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.202.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.202.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.202.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.203.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.203.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.203.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.204.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.204.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.204.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.205.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.205.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.205.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.206.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.206.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.206.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.207.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.207.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.207.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.208.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.208.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.208.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.209.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.209.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.209.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.21.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.21.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.21.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.210.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.210.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.210.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.211.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.211.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.211.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.212.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.212.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.212.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.213.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.213.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.213.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.214.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.214.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.214.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.215.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.215.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.215.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.216.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.216.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.216.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.217.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.217.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.217.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.218.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.218.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.218.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.219.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.219.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.219.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.22.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.22.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.22.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.220.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.220.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.220.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.221.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.221.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.221.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.222.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.222.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.222.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.223.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.223.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.223.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.224.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.224.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.224.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.225.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.225.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.225.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.226.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.226.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.226.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.227.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.227.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.227.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.228.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.228.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.228.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.229.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.229.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.229.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.23.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.23.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.23.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.230.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.230.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.230.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.231.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.231.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.231.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.232.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.232.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.232.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.233.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.233.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.233.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.234.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.234.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.234.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.235.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.235.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.235.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.236.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.236.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.236.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.237.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.237.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.237.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.238.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.238.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.238.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.239.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.239.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.239.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.24.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.24.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.24.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.240.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.240.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.240.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.241.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.241.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.241.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.242.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.242.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.242.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.243.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.243.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.243.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.244.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.244.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.244.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.245.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.245.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.245.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.246.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.246.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.246.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.247.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.247.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.247.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.248.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.248.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.248.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.249.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.249.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.249.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.25.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.25.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.25.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.250.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.250.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.250.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.251.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.251.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.251.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.252.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.252.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.252.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.253.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.253.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.253.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.254.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.254.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.254.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.255.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.255.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.255.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.26.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.26.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.26.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.27.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.27.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.27.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.28.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.28.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.28.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.29.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.29.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.29.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.3.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.3.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.3.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.30.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.30.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.30.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.31.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.31.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.31.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.32.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.32.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.32.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.33.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.33.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.33.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.34.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.34.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.34.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.35.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.35.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.35.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.36.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.36.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.36.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.37.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.37.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.37.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.38.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.38.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.38.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.39.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.39.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.39.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.4.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.4.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.4.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.40.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.40.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.40.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.41.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.41.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.41.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.42.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.42.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.42.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.43.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.43.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.43.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.44.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.44.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.44.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.45.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.45.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.45.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.46.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.46.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.46.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.47.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.47.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.47.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.48.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.48.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.48.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.49.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.49.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.49.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.5.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.5.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.5.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.50.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.50.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.50.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.51.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.51.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.51.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.52.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.52.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.52.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.53.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.53.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.53.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.54.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.54.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.54.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.55.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.55.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.55.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.56.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.56.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.56.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.57.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.57.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.57.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.58.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.58.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.58.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.59.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.59.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.59.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.6.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.6.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.6.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.60.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.60.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.60.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.61.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.61.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.61.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.62.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.62.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.62.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.63.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.63.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.63.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.64.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.64.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.64.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.65.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.65.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.65.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.66.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.66.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.66.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.67.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.67.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.67.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.68.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.68.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.68.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.69.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.69.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.69.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.7.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.7.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.7.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.70.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.70.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.70.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.71.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.71.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.71.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.72.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.72.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.72.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.73.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.73.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.73.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.74.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.74.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.74.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.75.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.75.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.75.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.76.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.76.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.76.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.77.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.77.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.77.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.78.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.78.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.78.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.79.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.79.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.79.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.8.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.8.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.8.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.80.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.80.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.80.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.81.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.81.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.81.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.82.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.82.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.82.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.83.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.83.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.83.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.84.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.84.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.84.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.85.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.85.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.85.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.86.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.86.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.86.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.87.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.87.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.87.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.88.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.88.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.88.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.89.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.89.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.89.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.9.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.9.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.9.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.90.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.90.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.90.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.91.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.91.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.91.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.92.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.92.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.92.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.93.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.93.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.93.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.94.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.94.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.94.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.95.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.95.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.95.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.96.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.96.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.96.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.97.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.97.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.97.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.98.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.98.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.98.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.99.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.99.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.experts.99.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.gate.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00016-of-00033.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.A_log": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.dt_bias": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.norm.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.0.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.1.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.1.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.10.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.10.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.100.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.100.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.100.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.101.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.101.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.101.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.102.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.102.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.103.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.103.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.103.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.104.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.104.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.105.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.105.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.105.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.106.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.106.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.106.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.107.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.107.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.107.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.108.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.108.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.108.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.109.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.109.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.109.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.11.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.11.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.11.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.110.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.110.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.110.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.111.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.111.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.111.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.112.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.112.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.112.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.113.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.113.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.113.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.114.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.114.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.114.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.115.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.115.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.115.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.116.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.116.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.116.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.117.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.117.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.117.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.118.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.118.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.118.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.119.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.119.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.119.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.12.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.12.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.12.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.120.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.120.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.120.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.121.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.121.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.121.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.122.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.122.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.123.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.123.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.123.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.124.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.124.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.124.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.125.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.125.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.125.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.126.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.126.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.126.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.127.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.127.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.128.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.128.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.128.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.129.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.129.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.129.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.13.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.13.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.13.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.130.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.130.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.130.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.131.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.131.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.131.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.132.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.132.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.132.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.133.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.133.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.133.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.134.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.134.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.134.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.135.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.135.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.135.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.136.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.136.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.136.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.137.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.137.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.137.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.138.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.138.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.138.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.139.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.139.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.139.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.14.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.14.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.14.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.140.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.140.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.140.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.141.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.141.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.141.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.142.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.142.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.142.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.143.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.143.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.143.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.144.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.144.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.144.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.145.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.145.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.145.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.146.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.146.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.146.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.147.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.147.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.147.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.148.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.148.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.148.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.149.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.149.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.149.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.15.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.15.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.15.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.150.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.150.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.150.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.151.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.151.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.151.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.152.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.152.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.152.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.153.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.153.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.153.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.154.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.154.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.154.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.155.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.155.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.155.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.156.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.156.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.156.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.157.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.157.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.157.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.158.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.158.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.158.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.159.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.159.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.159.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.16.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.16.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.16.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.160.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.160.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.160.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.161.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.161.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.161.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.162.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.162.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.162.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.163.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.163.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.163.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.164.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.164.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.164.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.165.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.165.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.165.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.166.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.166.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.166.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.167.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.167.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.167.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.168.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.168.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.168.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.169.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.169.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.169.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.17.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.17.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.17.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.170.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.170.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.170.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.171.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.171.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.171.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.172.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.172.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.172.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.173.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.173.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.173.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.174.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.174.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.174.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.175.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.175.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.175.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.176.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.176.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.176.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.177.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.177.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.177.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.178.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.178.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.178.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.179.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.179.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.179.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.18.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.18.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.18.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.180.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.180.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.180.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.181.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.181.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.181.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.182.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.182.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.182.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.183.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.183.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.183.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.184.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.184.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.184.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.185.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.185.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.185.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.186.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.186.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.186.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.187.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.187.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.187.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.188.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.188.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.188.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.189.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.189.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.189.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.19.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.19.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.19.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.190.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.190.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.190.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.191.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.191.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.191.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.192.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.192.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.192.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.193.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.193.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.193.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.194.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.194.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.194.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.195.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.195.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.195.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.196.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.196.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.196.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.197.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.197.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.197.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.198.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.198.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.198.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.199.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.199.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.199.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.2.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.2.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.2.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.20.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.20.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.20.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.200.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.200.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.200.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.201.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.201.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.201.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.202.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.202.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.202.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.203.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.203.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.203.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.204.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.204.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.204.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.205.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.205.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.205.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.206.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.206.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.206.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.207.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.207.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.207.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.208.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.208.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.208.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.209.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.209.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.209.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.21.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.21.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.210.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.210.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.210.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.211.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.211.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.211.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.212.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.212.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.212.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.213.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.213.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.213.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.214.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.214.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.214.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.215.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.215.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.215.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.216.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.216.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.216.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.217.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.217.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.217.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.218.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.218.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.218.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.219.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.219.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.219.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.22.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.22.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.22.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.220.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.220.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.220.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.221.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.221.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.221.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.222.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.222.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.222.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.223.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.223.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.223.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.224.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.224.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.224.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.225.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.225.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.225.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.226.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.226.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.226.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.227.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.227.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.227.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.228.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.228.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.228.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.229.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.229.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.229.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.23.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.23.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.23.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.230.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.230.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.230.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.231.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.231.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.231.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.232.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.232.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.232.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.233.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.233.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.233.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.234.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.234.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.234.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.235.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.235.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.235.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.236.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.236.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.236.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.237.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.237.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.237.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.238.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.238.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.238.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.239.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.239.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.239.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.24.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.24.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.24.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.240.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.240.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.240.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.241.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.241.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.241.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.242.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.242.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.242.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.243.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.243.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.243.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.244.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.244.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.244.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.245.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.245.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.245.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.246.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.246.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.246.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.247.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.247.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.247.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.248.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.248.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.248.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.249.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.249.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.249.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.25.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.25.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.25.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.250.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.250.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.250.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.251.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.251.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.251.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.252.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.252.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.252.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.253.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.253.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.253.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.254.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.254.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.254.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.255.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.255.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.255.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.26.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.26.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.26.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.27.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.27.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.27.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.28.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.28.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.28.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.29.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.29.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.3.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.3.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.3.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.30.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.30.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.30.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.31.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.31.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.31.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.32.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.32.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.32.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.33.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.33.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.33.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.34.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.34.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.34.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.35.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.35.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.35.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.36.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.36.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.36.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.37.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.37.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.37.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.38.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.38.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.38.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.39.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.39.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.39.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.4.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.4.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.4.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.40.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.40.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.40.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.41.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.41.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.41.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.42.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.42.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.42.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.43.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.43.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.43.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.44.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.44.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.44.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.45.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.45.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.45.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.46.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.46.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.47.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.47.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.47.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.48.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.48.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.48.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.49.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.49.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.49.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.5.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.5.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.5.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.50.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.50.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.50.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.51.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.51.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.52.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.52.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.52.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.53.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.53.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.53.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.54.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.54.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.54.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.55.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.55.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.55.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.56.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.56.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.56.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.57.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.57.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.57.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.58.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.58.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.58.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.59.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.59.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.59.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.6.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.6.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.6.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.60.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.60.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.60.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.61.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.61.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.62.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.62.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.62.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.63.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.63.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.63.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.64.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.64.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.64.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.65.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.65.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.65.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.66.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.66.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.66.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.67.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.67.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.67.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.68.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.68.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.68.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.69.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.69.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.69.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.7.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.7.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.7.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.70.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.70.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.70.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.71.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.71.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.71.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.72.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.72.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.72.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.73.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.73.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.73.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.74.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.74.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.74.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.75.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.75.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.75.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.76.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.76.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.76.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.77.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.77.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.77.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.78.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.78.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.78.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.79.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.79.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.79.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.8.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.8.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.8.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.80.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.80.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.80.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.81.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.81.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.81.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.82.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.82.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.82.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.83.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.83.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.83.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.84.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.84.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.84.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.85.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.85.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.85.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.86.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.86.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.86.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.87.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.87.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.87.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.88.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.88.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.88.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.89.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.89.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.89.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.9.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.9.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.9.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.90.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.90.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.90.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.91.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.91.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.91.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.92.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.92.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.92.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.93.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.93.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.93.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.94.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.94.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.94.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.95.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.95.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.95.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.96.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.96.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.96.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.97.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.97.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.97.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.98.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.98.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.98.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.99.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.99.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.experts.99.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.gate.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.A_log": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.dt_bias": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.norm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.0.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.0.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.0.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.1.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.1.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.1.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.10.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.10.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.10.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.100.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.100.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.100.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.101.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.101.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.101.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.102.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.102.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.102.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.103.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.103.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.103.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.104.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.104.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.104.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.105.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.105.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.105.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.106.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.106.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.106.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.107.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.107.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.107.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.108.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.108.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.108.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.109.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.109.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.109.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.11.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.11.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.11.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.110.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.110.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.110.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.111.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.111.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.111.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.112.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.112.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.112.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.113.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.113.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.113.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.114.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.114.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.114.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.115.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.115.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.115.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.116.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.116.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.116.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.117.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.117.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.117.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.118.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.118.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.118.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.119.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.119.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.119.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.12.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.12.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.12.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.120.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.120.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.120.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.121.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.121.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.121.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.122.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.122.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.122.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.123.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.123.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.123.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.124.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.124.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.124.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.125.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.125.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.125.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.126.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.126.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.126.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.127.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.127.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.127.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.128.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.128.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.128.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.129.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.129.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.129.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.13.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.13.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.13.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.130.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.130.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.130.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.131.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.131.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.131.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.132.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.132.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.132.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.133.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.133.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.133.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.134.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.134.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.134.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.135.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.135.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.135.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.136.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.136.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.136.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.137.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.137.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.137.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.138.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.138.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.138.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.139.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.139.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.139.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.14.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.14.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.14.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.140.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.140.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.140.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.141.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.141.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.141.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.142.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.142.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.142.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.143.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.143.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.143.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.144.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.144.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.144.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.145.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.145.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.145.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.146.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.146.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.146.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.147.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.147.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.147.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.148.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.148.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.148.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.149.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.149.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.149.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.15.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.15.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.15.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.150.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.150.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.150.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.151.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.151.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.151.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.152.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.152.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.152.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.153.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.153.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.153.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.154.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.154.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.154.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.155.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.155.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.155.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.156.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.156.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.156.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.157.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.157.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.157.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.158.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.158.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.158.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.159.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.159.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.159.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.16.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.16.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.16.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.160.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.160.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.160.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.161.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.161.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.161.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.162.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.162.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.162.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.163.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.163.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.163.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.164.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.164.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.164.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.165.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.165.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.165.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.166.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.166.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.166.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.167.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.167.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.167.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.168.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.168.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.168.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.169.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.169.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.169.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.17.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.17.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.17.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.170.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.170.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.170.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.171.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.171.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.171.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.172.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.172.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.172.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.173.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.173.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.173.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.174.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.174.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.174.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.175.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.175.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.175.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.176.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.176.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.176.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.177.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.177.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.177.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.178.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.178.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.178.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.179.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.179.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.179.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.18.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.18.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.18.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.180.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.180.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.180.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.181.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.181.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.181.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.182.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.182.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.182.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.183.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.183.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.183.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.184.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.184.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.184.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.185.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.185.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.185.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.186.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.186.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.186.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.187.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.187.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.187.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.188.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.188.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.188.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.189.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.189.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.189.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.19.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.19.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.19.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.190.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.190.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.190.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.191.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.191.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.191.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.192.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.192.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.192.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.193.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.193.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.193.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.194.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.194.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.194.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.195.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.195.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.195.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.196.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.196.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.196.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.197.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.197.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.197.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.198.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.198.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.198.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.199.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.199.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.199.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.2.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.2.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.2.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.20.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.20.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.20.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.200.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.200.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.200.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.201.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.201.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.201.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.202.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.202.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.202.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.203.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.203.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.203.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.204.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.204.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.204.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.205.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.205.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.205.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.206.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.206.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.206.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.207.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.207.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.207.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.208.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.208.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.208.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.209.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.209.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.209.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.21.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.21.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.21.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.210.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.210.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.210.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.211.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.211.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.211.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.212.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.212.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.212.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.213.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.213.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.213.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.214.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.214.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.214.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.215.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.215.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.215.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.216.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.216.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.216.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.217.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.217.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.217.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.218.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.218.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.218.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.219.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.219.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.219.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.22.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.22.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.22.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.220.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.220.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.220.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.221.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.221.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.221.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.222.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.222.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.222.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.223.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.223.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.223.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.224.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.224.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.224.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.225.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.225.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.225.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.226.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.226.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.226.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.227.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.227.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.227.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.228.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.228.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.228.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.229.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.229.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.229.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.23.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.23.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.23.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.230.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.230.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.230.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.231.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.231.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.231.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.232.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.232.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.232.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.233.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.233.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.233.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.234.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.234.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.234.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.235.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.235.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.235.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.236.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.236.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.236.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.237.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.237.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.237.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.238.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.238.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.238.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.239.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.239.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.239.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.24.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.24.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.24.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.240.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.240.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.240.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.241.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.241.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.241.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.242.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.242.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.242.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.243.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.243.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.243.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.244.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.244.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.244.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.245.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.245.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.245.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.246.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.246.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.246.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.247.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.247.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.247.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.248.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.248.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.248.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.249.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.249.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.249.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.25.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.25.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.25.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.250.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.250.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.250.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.251.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.251.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.251.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.252.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.252.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.252.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.253.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.253.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.253.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.254.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.254.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.254.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.255.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.255.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.255.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.26.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.26.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.26.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.27.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.27.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.27.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.28.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.28.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.28.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.29.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.29.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.29.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.3.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.3.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.3.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.30.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.30.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.30.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.31.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.31.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.31.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.32.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.32.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.32.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.33.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.33.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.33.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.34.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.34.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.34.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.35.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.35.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.35.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.36.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.36.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.36.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.37.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.37.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.37.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.38.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.38.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.38.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.39.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.39.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.39.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.4.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.4.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.4.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.40.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.40.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.40.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.41.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.41.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.41.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.42.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.42.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.42.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.43.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.43.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.43.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.44.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.44.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.44.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.45.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.45.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.45.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.46.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.46.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.46.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.47.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.47.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.47.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.48.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.48.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.48.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.49.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.49.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.49.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.5.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.5.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.5.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.50.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.50.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.50.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.51.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.51.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.51.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.52.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.52.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.52.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.53.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.53.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.53.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.54.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.54.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.54.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.55.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.55.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.55.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.56.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.56.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.56.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.57.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.57.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.57.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.58.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.58.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.58.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.59.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.59.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.59.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.6.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.6.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.6.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.60.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.60.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.60.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.61.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.61.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.61.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.62.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.62.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.62.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.63.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.63.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.63.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.64.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.64.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.64.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.65.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.65.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.65.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.66.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.66.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.66.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.67.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.67.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.67.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.68.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.68.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.68.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.69.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.69.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.69.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.7.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.7.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.7.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.70.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.70.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.70.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.71.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.71.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.71.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.72.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.72.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.72.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.73.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.73.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.73.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.74.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.74.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.74.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.75.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.75.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.75.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.76.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.76.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.76.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.77.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.77.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.77.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.78.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.78.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.78.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.79.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.79.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.79.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.8.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.8.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.8.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.80.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.80.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.80.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.81.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.81.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.81.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.82.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.82.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.82.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.83.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.83.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.83.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.84.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.84.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.84.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.85.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.85.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.85.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.86.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.86.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.86.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.87.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.87.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.87.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.88.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.88.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.88.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.89.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.89.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.89.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.9.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.9.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.9.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.90.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.90.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.90.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.91.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.91.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.91.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.92.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.92.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.92.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.93.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.93.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.93.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.94.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.94.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.94.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.95.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.95.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.95.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.96.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.96.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.96.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.97.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.97.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.97.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.98.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.98.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.98.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.99.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.99.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.experts.99.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.gate.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.A_log": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.dt_bias": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.norm.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.0.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.0.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.0.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.1.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.1.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.1.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.10.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.10.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.10.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.100.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.100.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.100.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.101.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.101.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.101.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.102.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.102.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.102.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.103.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.103.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.103.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.104.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.104.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.104.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.105.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.105.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.105.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.106.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.106.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.106.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.107.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.107.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.107.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.108.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.108.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.108.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.109.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.109.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.109.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.11.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.11.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.11.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.110.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.110.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.110.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.111.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.111.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.111.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.112.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.112.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.112.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.113.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.113.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.113.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.114.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.114.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.114.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.115.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.115.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.115.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.116.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.116.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.116.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.117.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.117.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.117.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.118.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.118.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.118.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.119.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.119.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.119.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.12.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.12.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.12.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.120.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.120.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.120.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.121.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.121.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.121.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.122.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.122.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.122.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.123.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.123.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.123.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.124.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.124.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.124.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.125.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.125.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.125.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.126.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.126.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.126.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.127.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.127.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.127.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.128.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.128.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.128.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.129.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.129.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.129.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.13.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.13.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.13.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.130.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.130.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.130.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.131.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.131.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.131.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.132.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.132.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.132.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.133.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.133.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.133.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.134.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.134.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.134.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.135.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.135.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.135.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.136.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.136.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.136.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.137.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.137.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.137.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.138.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.138.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.138.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.139.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.139.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.139.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.14.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.14.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.14.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.140.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.140.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.140.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.141.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.141.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.141.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.142.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.142.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.142.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.143.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.143.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.143.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.144.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.144.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.144.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.145.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.145.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.145.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.146.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.146.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.146.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.147.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.147.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.147.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.148.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.148.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.148.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.149.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.149.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.149.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.15.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.15.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.15.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.150.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.150.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.150.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.151.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.151.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.151.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.152.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.152.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.152.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.153.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.153.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.153.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.154.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.154.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.154.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.155.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.155.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.155.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.156.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.156.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.156.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.157.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.157.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.157.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.158.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.158.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.158.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.159.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.159.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.159.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.16.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.16.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.16.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.160.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.160.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.160.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.161.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.161.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.161.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.162.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.162.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.162.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.163.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.163.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.163.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.164.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.164.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.164.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.165.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.165.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.165.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.166.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.166.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.166.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.167.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.167.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.167.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.168.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.168.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.168.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.169.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.169.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.169.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.17.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.17.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.17.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.170.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.170.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.170.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.171.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.171.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.171.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.172.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.172.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.172.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.173.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.173.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.173.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.174.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.174.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.174.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.175.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.175.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.175.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.176.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.176.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.176.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.177.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.177.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.177.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.178.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.178.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.178.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.179.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.179.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.179.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.18.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.18.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.18.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.180.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.180.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.180.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.181.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.181.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.181.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.182.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.182.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.182.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.183.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.183.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.183.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.184.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.184.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.184.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.185.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.185.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.185.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.186.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.186.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.186.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.187.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.187.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.187.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.188.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.188.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.188.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.189.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.189.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.189.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.19.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.19.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.19.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.190.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.190.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.190.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.191.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.191.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.191.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.192.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.192.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.192.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.193.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.193.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.193.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.194.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.194.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.194.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.195.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.195.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.195.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.196.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.196.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.196.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.197.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.197.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.197.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.198.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.198.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.198.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.199.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.199.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.199.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.2.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.2.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.2.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.20.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.20.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.20.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.200.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.200.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.200.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.201.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.201.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.201.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.202.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.202.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.202.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.203.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.203.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.203.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.204.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.204.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.204.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.205.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.205.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.205.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.206.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.206.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.206.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.207.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.207.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.207.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.208.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.208.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.208.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.209.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.209.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.209.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.21.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.21.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.21.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.210.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.210.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.210.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.211.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.211.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.211.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.212.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.212.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.212.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.213.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.213.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.213.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.214.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.214.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.214.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.215.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.215.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.215.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.216.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.216.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.216.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.217.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.217.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.217.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.218.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.218.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.218.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.219.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.219.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.219.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.22.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.22.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.22.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.220.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.220.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.220.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.221.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.221.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.221.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.222.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.222.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.222.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.223.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.223.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.223.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.224.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.224.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.224.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.225.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.225.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.225.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.226.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.226.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.226.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.227.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.227.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.227.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.228.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.228.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.228.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.229.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.229.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.229.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.23.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.23.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.23.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.230.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.230.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.230.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.231.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.231.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.231.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.232.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.232.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.232.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.233.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.233.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.233.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.234.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.234.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.234.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.235.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.235.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.235.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.236.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.236.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.236.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.237.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.237.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.237.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.238.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.238.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.238.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.239.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.239.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.239.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.24.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.24.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.24.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.240.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.240.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.240.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.241.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.241.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.241.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.242.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.242.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.242.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.243.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.243.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.243.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.244.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.244.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.244.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.245.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.245.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.245.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.246.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.246.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.246.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.247.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.247.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.247.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.248.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.248.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.248.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.249.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.249.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.249.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.25.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.25.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.25.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.250.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.250.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.250.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.251.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.251.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.251.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.252.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.252.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.252.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.253.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.253.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.253.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.254.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.254.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.254.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.255.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.255.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.255.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.26.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.26.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.26.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.27.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.27.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.27.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.28.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.28.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.28.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.29.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.29.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.29.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.3.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.3.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.3.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.30.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.30.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.30.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.31.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.31.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.31.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.32.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.32.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.32.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.33.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.33.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.33.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.34.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.34.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.34.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.35.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.35.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.35.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.36.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.36.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.36.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.37.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.37.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.37.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.38.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.38.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.38.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.39.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.39.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.39.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.4.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.4.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.4.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.40.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.40.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.40.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.41.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.41.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.41.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.42.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.42.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.42.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.43.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.43.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.43.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.44.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.44.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.44.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.45.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.45.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.45.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.46.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.46.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.46.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.47.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.47.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.47.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.48.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.48.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.48.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.49.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.49.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.49.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.5.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.5.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.5.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.50.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.50.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.50.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.51.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.51.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.51.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.52.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.52.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.52.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.53.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.53.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.53.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.54.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.54.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.54.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.55.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.55.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.55.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.56.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.56.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.56.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.57.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.57.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.57.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.58.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.58.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.58.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.59.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.59.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.59.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.6.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.6.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.6.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.60.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.60.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.60.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.61.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.61.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.61.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.62.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.62.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.62.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.63.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.63.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.63.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.64.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.64.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.64.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.65.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.65.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.65.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.66.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.66.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.66.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.67.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.67.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.67.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.68.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.68.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.68.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.69.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.69.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.69.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.7.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.7.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.7.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.70.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.70.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.70.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.71.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.71.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.71.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.72.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.72.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.72.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.73.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.73.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.73.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.74.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.74.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.74.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.75.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.75.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.75.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.76.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.76.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.76.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.77.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.77.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.77.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.78.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.78.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.78.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.79.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.79.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.79.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.8.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.8.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.8.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.80.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.80.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.80.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.81.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.81.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.81.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.82.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.82.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.82.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.83.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.83.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.83.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.84.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.84.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.84.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.85.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.85.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.85.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.86.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.86.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.86.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.87.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.87.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.87.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.88.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.88.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.88.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.89.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.89.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.89.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.9.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.9.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.9.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.90.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.90.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.90.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.91.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.91.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.91.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.92.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.92.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.92.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.93.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.93.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.93.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.94.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.94.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.94.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.95.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.95.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.95.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.96.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.96.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.96.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.97.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.97.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.97.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.98.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.98.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.98.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.99.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.99.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.experts.99.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.21.mlp.gate.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00017-of-00033.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.A_log": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.dt_bias": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.norm.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.0.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.0.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.0.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.1.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.1.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.1.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.10.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.10.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.10.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.100.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.100.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.100.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.101.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.101.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.101.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.102.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.102.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.102.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.103.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.103.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.103.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.104.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.104.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.104.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.105.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.105.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.105.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.106.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.106.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.106.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.107.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.107.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.107.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.108.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.108.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.108.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.109.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.109.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.109.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.11.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.11.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.11.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.110.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.110.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.110.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.111.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.111.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.111.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.112.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.112.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.112.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.113.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.113.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.113.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.114.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.114.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.114.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.115.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.115.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.115.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.116.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.116.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.116.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.117.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.117.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.117.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.118.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.118.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.118.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.119.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.119.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.119.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.12.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.12.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.12.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.120.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.120.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.120.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.121.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.121.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.121.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.122.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.122.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.122.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.123.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.123.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.123.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.124.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.124.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.124.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.125.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.125.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.125.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.126.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.126.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.126.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.127.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.127.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.127.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.128.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.128.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.128.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.129.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.129.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.129.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.13.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.13.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.13.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.130.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.130.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.130.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.131.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.131.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.131.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.132.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.132.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.132.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.133.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.133.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.133.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.134.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.134.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.134.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.135.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.135.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.135.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.136.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.136.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.136.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.137.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.137.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.137.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.138.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.138.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.138.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.139.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.139.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.139.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.14.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.14.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.14.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.140.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.140.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.140.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.141.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.141.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.141.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.142.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.142.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.142.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.143.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.143.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.143.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.144.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.144.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.144.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.145.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.145.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.145.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.146.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.146.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.146.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.147.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.147.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.147.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.148.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.148.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.148.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.149.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.149.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.149.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.15.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.15.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.15.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.150.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.150.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.150.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.151.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.151.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.151.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.152.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.152.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.152.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.153.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.153.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.153.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.154.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.154.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.154.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.155.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.155.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.155.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.156.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.156.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.156.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.157.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.157.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.157.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.158.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.158.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.158.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.159.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.159.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.159.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.16.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.16.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.16.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.160.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.160.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.160.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.161.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.161.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.161.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.162.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.162.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.162.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.163.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.163.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.163.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.164.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.164.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.164.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.165.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.165.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.165.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.166.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.166.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.166.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.167.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.167.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.167.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.168.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.168.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.168.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.169.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.169.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.169.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.17.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.17.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.17.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.170.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.170.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.170.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.171.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.171.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.171.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.172.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.172.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.172.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.173.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.173.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.173.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.174.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.174.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.174.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.175.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.175.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.175.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.176.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.176.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.176.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.177.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.177.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.177.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.178.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.178.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.178.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.179.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.179.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.179.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.18.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.18.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.18.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.180.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.180.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.180.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.181.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.181.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.181.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.182.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.182.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.182.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.183.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.183.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.183.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.184.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.184.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.184.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.185.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.185.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.185.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.186.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.186.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.186.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.187.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.187.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.187.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.188.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.188.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.188.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.189.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.189.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.189.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.19.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.19.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.19.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.190.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.190.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.190.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.191.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.191.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.191.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.192.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.192.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.192.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.193.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.193.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.193.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.194.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.194.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.194.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.195.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.195.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.195.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.196.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.196.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.196.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.197.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.197.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.197.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.198.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.198.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.198.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.199.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.199.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.199.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.2.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.2.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.2.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.20.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.20.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.20.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.200.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.200.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.200.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.201.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.201.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.201.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.202.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.202.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.202.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.203.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.203.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.203.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.204.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.204.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.204.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.205.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.205.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.205.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.206.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.206.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.206.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.207.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.207.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.207.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.208.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.208.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.208.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.209.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.209.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.209.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.21.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.21.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.21.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.210.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.210.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.210.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.211.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.211.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.211.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.212.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.212.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.212.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.213.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.213.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.213.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.214.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.214.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.214.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.215.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.215.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.215.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.216.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.216.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.216.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.217.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.217.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.217.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.218.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.218.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.218.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.219.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.219.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.219.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.22.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.22.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.22.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.220.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.220.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.220.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.221.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.221.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.221.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.222.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.222.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.222.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.223.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.223.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.223.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.224.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.224.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.224.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.225.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.225.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.225.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.226.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.226.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.226.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.227.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.227.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.227.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.228.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.228.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.228.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.229.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.229.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.229.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.23.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.23.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.23.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.230.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.230.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.230.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.231.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.231.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.231.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.232.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.232.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.232.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.233.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.233.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.233.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.234.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.234.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.234.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.235.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.235.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.235.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.236.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.236.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.236.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.237.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.237.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.237.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.238.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.238.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.238.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.239.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.239.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.239.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.24.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.24.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.24.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.240.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.240.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.240.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.241.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.241.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.241.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.242.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.242.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.242.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.243.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.243.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.243.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.244.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.244.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.244.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.245.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.245.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.245.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.246.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.246.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.246.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.247.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.247.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.247.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.248.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.248.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.248.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.249.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.249.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.249.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.25.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.25.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.25.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.250.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.250.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.250.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.251.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.251.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.251.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.252.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.252.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.252.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.253.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.253.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.253.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.254.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.254.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.254.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.255.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.255.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.255.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.26.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.26.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.26.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.27.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.27.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.27.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.28.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.28.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.28.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.29.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.29.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.29.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.3.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.3.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.3.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.30.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.30.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.30.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.31.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.31.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.31.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.32.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.32.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.32.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.33.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.33.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.33.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.34.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.34.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.34.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.35.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.35.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.35.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.36.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.36.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.36.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.37.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.37.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.37.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.38.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.38.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.38.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.39.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.39.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.39.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.4.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.4.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.4.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.40.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.40.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.40.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.41.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.41.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.41.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.42.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.42.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.42.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.43.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.43.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.43.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.44.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.44.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.44.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.45.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.45.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.45.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.46.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.46.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.46.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.47.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.47.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.47.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.48.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.48.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.48.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.49.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.49.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.49.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.5.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.5.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.5.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.50.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.50.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.50.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.51.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.51.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.51.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.52.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.52.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.52.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.53.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.53.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.53.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.54.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.54.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.54.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.55.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.55.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.55.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.56.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.56.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.56.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.57.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.57.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.57.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.58.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.58.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.58.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.59.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.59.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.59.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.6.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.6.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.6.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.60.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.60.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.60.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.61.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.61.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.61.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.62.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.62.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.62.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.63.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.63.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.63.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.64.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.64.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.64.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.65.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.65.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.65.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.66.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.66.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.66.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.67.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.67.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.67.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.68.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.68.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.68.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.69.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.69.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.69.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.7.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.7.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.7.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.70.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.70.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.70.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.71.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.71.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.71.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.72.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.72.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.72.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.73.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.73.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.73.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.74.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.74.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.74.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.75.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.75.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.75.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.76.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.76.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.76.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.77.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.77.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.77.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.78.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.78.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.78.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.79.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.79.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.79.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.8.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.8.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.8.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.80.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.80.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.80.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.81.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.81.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.81.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.82.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.82.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.82.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.83.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.83.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.83.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.84.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.84.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.84.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.85.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.85.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.85.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.86.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.86.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.86.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.87.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.87.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.87.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.88.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.88.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.88.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.89.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.89.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.89.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.9.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.9.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.9.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.90.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.90.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.90.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.91.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.91.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.91.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.92.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.92.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.92.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.93.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.93.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.93.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.94.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.94.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.94.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.95.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.95.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.95.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.96.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.96.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.96.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.97.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.97.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.97.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.98.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.98.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.98.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.99.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.99.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.experts.99.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.22.mlp.gate.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00018-of-00033.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.0.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.0.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.0.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.1.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.1.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.1.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.10.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.10.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.10.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.100.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.100.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.100.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.101.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.101.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.101.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.102.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.102.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.102.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.103.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.103.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.103.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.104.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.104.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.104.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.105.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.105.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.105.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.106.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.106.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.106.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.107.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.107.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.107.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.108.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.108.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.108.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.109.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.109.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.109.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.11.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.11.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.11.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.110.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.110.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.110.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.111.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.111.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.111.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.112.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.112.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.112.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.113.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.113.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.113.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.114.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.114.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.114.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.115.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.115.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.115.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.116.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.116.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.116.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.117.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.117.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.117.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.118.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.118.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.118.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.119.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.119.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.119.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.12.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.12.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.12.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.120.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.120.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.120.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.121.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.121.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.121.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.122.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.122.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.122.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.123.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.123.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.123.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.124.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.124.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.124.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.125.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.125.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.125.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.126.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.126.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.126.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.127.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.127.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.127.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.128.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.128.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.128.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.129.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.129.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.129.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.13.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.13.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.13.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.130.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.130.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.130.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.131.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.131.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.131.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.132.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.132.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.132.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.133.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.133.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.133.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.134.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.134.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.134.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.135.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.135.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.135.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.136.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.136.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.136.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.137.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.137.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.137.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.138.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.138.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.138.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.139.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.139.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.139.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.14.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.14.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.14.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.140.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.140.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.140.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.141.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.141.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.141.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.142.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.142.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.142.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.143.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.143.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.143.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.144.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.144.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.144.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.145.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.145.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.145.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.146.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.146.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.146.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.147.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.147.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.147.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.148.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.148.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.148.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.149.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.149.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.149.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.15.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.15.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.15.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.150.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.150.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.150.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.151.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.151.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.151.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.152.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.152.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.152.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.153.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.153.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.153.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.154.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.154.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.154.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.155.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.155.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.155.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.156.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.156.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.156.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.157.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.157.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.157.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.158.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.158.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.158.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.159.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.159.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.159.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.16.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.16.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.16.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.160.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.160.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.160.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.161.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.161.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.161.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.162.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.162.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.162.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.163.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.163.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.163.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.164.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.164.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.164.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.165.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.165.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.165.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.166.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.166.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.166.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.167.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.167.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.167.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.168.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.168.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.168.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.169.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.169.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.169.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.17.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.17.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.17.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.170.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.170.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.170.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.171.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.171.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.171.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.172.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.172.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.172.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.173.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.173.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.173.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.174.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.174.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.174.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.175.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.175.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.175.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.176.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.176.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.176.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.177.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.177.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.177.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.178.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.178.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.178.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.179.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.179.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.179.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.18.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.18.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.18.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.180.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.180.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.180.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.181.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.181.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.181.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.182.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.182.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.182.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.183.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.183.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.183.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.184.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.184.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.184.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.185.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.185.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.185.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.186.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.186.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.186.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.187.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.187.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.187.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.188.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.188.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.188.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.189.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.189.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.189.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.19.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.19.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.19.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.190.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.190.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.190.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.191.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.191.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.191.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.192.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.192.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.192.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.193.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.193.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.193.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.194.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.194.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.194.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.195.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.195.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.195.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.196.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.196.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.196.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.197.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.197.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.197.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.198.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.198.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.198.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.199.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.199.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.199.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.2.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.2.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.2.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.20.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.20.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.20.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.200.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.200.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.200.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.201.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.201.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.201.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.202.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.202.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.202.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.203.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.203.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.203.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.204.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.204.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.204.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.205.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.205.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.205.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.206.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.206.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.206.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.207.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.207.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.207.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.208.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.208.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.208.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.209.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.209.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.209.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.21.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.21.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.21.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.210.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.210.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.210.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.211.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.211.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.211.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.212.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.212.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.212.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.213.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.213.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.213.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.214.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.214.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.214.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.215.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.215.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.215.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.216.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.216.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.216.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.217.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.217.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.217.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.218.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.218.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.218.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.219.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.219.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.219.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.22.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.22.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.22.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.220.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.220.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.220.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.221.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.221.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.221.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.222.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.222.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.222.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.223.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.223.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.223.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.224.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.224.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.224.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.225.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.225.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.225.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.226.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.226.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.226.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.227.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.227.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.227.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.228.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.228.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.228.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.229.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.229.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.229.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.23.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.23.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.23.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.230.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.230.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.230.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.231.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.231.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.231.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.232.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.232.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.232.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.233.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.233.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.233.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.234.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.234.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.234.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.235.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.235.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.235.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.236.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.236.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.236.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.237.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.237.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.237.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.238.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.238.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.238.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.239.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.239.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.239.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.24.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.24.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.24.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.240.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.240.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.240.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.241.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.241.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.241.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.242.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.242.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.242.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.243.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.243.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.243.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.244.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.244.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.244.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.245.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.245.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.245.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.246.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.246.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.246.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.247.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.247.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.247.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.248.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.248.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.248.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.249.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.249.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.249.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.25.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.25.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.25.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.250.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.250.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.250.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.251.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.251.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.251.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.252.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.252.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.252.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.253.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.253.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.253.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.254.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.254.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.254.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.255.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.255.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.255.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.26.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.26.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.26.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.27.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.27.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.27.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.28.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.28.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.28.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.29.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.29.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.29.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.3.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.3.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.3.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.30.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.30.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.30.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.31.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.31.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.31.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.32.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.32.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.32.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.33.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.33.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.33.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.34.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.34.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.34.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.35.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.35.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.35.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.36.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.36.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.36.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.37.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.37.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.37.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.38.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.38.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.38.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.39.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.39.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.39.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.4.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.4.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.4.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.40.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.40.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.40.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.41.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.41.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.41.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.42.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.42.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.42.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.43.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.43.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.43.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.44.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.44.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.44.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.45.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.45.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.45.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.46.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.46.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.46.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.47.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.47.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.47.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.48.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.48.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.48.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.49.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.49.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.49.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.5.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.5.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.5.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.50.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.50.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.50.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.51.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.51.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.51.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.52.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.52.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.52.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.53.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.53.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.53.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.54.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.54.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.54.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.55.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.55.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.55.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.56.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.56.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.56.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.57.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.57.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.57.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.58.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.58.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.58.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.59.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.59.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.59.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.6.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.6.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.6.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.60.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.60.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.60.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.61.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.61.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.61.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.62.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.62.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.62.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.63.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.63.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.63.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.64.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.64.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.64.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.65.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.65.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.65.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.66.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.66.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.66.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.67.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.67.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.67.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.68.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.68.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.68.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.69.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.69.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.69.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.7.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.7.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.7.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.70.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.70.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.70.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.71.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.71.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.71.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.72.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.72.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.72.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.73.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.73.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.73.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.74.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.74.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.74.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.75.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.75.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.75.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.76.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.76.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.76.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.77.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.77.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.77.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.78.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.78.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.78.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.79.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.79.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.79.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.8.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.8.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.8.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.80.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.80.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.80.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.81.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.81.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.81.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.82.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.82.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.82.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.83.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.83.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.83.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.84.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.84.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.84.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.85.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.85.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.85.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.86.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.86.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.86.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.87.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.87.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.87.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.88.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.88.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.88.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.89.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.89.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.89.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.9.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.9.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.9.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.90.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.90.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.90.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.91.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.91.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.91.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.92.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.92.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.92.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.93.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.93.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.93.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.94.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.94.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.94.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.95.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.95.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.95.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.96.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.96.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.96.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.97.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.97.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.97.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.98.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.98.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.98.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.99.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.99.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.experts.99.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.gate.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.A_log": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.dt_bias": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.norm.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.0.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.0.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.0.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.1.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.1.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.1.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.10.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.10.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.10.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.100.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.100.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.100.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.101.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.101.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.101.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.102.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.102.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.102.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.103.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.103.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.103.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.104.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.104.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.104.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.105.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.105.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.105.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.106.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.106.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.106.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.107.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.107.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.107.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.108.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.108.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.108.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.109.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.109.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.109.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.11.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.11.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.11.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.110.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.110.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.110.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.111.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.111.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.111.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.112.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.112.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.112.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.113.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.113.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.113.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.114.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.114.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.114.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.115.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.115.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.115.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.116.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.116.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.116.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.117.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.117.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.117.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.118.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.118.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.118.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.119.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.119.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.119.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.12.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.12.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.12.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.120.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.120.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.120.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.121.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.121.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.121.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.122.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.122.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.122.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.123.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.123.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.123.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.124.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.124.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.124.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.125.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.125.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.125.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.126.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.126.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.126.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.127.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.127.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.127.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.128.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.128.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.128.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.129.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.129.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.129.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.13.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.13.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.13.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.130.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.130.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.130.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.131.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.131.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.131.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.132.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.132.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.132.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.133.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.133.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.133.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.134.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.134.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.134.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.135.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.135.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.135.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.136.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.136.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.136.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.137.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.137.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.137.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.138.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.138.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.138.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.139.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.139.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.139.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.14.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.14.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.14.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.140.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.140.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.140.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.141.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.141.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.141.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.142.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.142.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.142.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.143.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.143.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.143.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.144.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.144.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.144.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.145.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.145.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.145.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.146.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.146.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.146.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.147.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.147.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.147.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.148.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.148.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.148.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.149.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.149.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.149.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.15.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.15.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.15.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.150.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.150.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.150.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.151.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.151.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.151.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.152.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.152.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.152.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.153.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.153.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.153.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.154.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.154.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.154.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.155.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.155.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.155.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.156.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.156.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.156.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.157.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.157.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.157.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.158.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.158.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.158.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.159.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.159.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.159.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.16.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.16.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.16.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.160.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.160.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.160.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.161.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.161.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.161.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.162.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.162.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.162.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.163.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.163.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.163.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.164.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.164.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.164.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.165.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.165.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.165.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.166.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.166.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.166.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.167.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.167.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.167.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.168.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.168.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.168.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.169.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.169.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.169.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.17.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.17.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.17.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.170.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.170.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.170.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.171.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.171.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.171.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.172.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.172.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.172.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.173.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.173.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.173.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.174.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.174.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.174.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.175.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.175.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.175.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.176.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.176.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.176.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.177.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.177.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.177.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.178.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.178.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.178.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.179.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.179.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.179.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.18.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.18.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.18.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.180.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.180.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.180.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.181.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.181.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.181.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.182.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.182.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.182.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.183.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.183.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.183.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.184.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.184.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.184.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.185.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.185.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.185.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.186.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.186.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.186.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.187.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.187.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.187.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.188.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.188.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.188.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.189.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.189.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.189.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.19.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.19.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.19.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.190.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.190.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.190.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.191.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.191.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.191.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.192.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.192.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.192.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.193.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.193.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.193.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.194.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.194.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.194.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.195.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.195.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.195.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.196.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.196.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.196.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.197.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.197.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.197.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.198.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.198.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.198.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.199.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.199.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.199.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.2.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.2.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.2.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.20.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.20.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.20.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.200.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.200.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.200.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.201.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.201.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.201.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.202.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.202.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.202.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.203.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.203.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.203.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.204.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.204.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.204.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.205.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.205.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.205.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.206.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.206.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.206.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.207.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.207.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.207.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.208.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.208.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.208.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.209.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.209.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.209.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.21.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.21.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.21.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.210.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.210.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.210.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.211.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.211.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.211.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.212.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.212.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.212.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.213.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.213.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.213.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.214.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.214.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.214.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.215.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.215.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.215.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.216.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.216.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.216.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.217.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.217.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.217.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.218.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.218.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.218.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.219.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.219.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.219.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.22.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.22.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.22.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.220.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.220.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.220.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.221.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.221.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.221.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.222.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.222.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.222.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.223.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.223.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.223.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.224.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.224.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.224.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.225.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.225.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.225.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.226.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.226.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.226.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.227.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.227.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.227.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.228.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.228.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.228.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.229.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.229.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.229.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.23.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.23.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.23.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.230.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.230.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.230.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.231.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.231.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.231.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.232.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.232.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.232.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.233.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.233.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.233.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.234.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.234.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.234.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.235.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.235.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.235.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.236.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.236.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.236.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.237.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.237.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.237.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.238.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.238.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.238.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.239.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.239.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.239.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.24.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.24.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.24.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.240.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.240.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.240.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.241.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.241.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.241.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.242.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.242.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.242.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.243.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.243.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.243.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.244.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.244.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.244.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.245.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.245.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.245.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.246.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.246.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.246.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.247.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.247.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.247.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.248.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.248.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.248.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.249.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.249.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.249.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.25.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.25.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.25.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.250.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.250.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.250.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.251.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.251.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.251.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.252.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.252.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.252.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.253.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.253.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.253.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.254.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.254.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.254.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.255.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.255.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.255.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.26.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.26.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.26.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.27.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.27.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.27.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.28.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.28.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.28.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.29.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.29.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.29.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.3.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.3.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.3.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.30.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.30.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.30.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.31.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.31.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.31.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.32.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.32.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.32.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.33.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.33.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.33.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.34.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.34.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.34.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.35.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.35.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.35.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.36.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.36.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.36.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.37.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.37.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.37.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.38.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.38.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.38.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.39.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.39.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.39.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.4.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.4.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.4.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.40.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.40.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.40.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.41.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.41.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.41.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.42.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.42.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.42.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.43.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.43.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.43.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.44.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.44.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.44.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.45.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.45.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.45.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.46.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.46.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.46.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.47.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.47.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.47.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.48.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.48.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.48.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.49.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.49.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.49.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.5.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.5.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.5.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.50.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.50.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.50.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.51.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.51.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.51.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.52.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.52.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.52.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.53.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.53.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.53.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.54.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.54.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.54.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.55.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.55.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.55.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.56.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.56.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.56.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.57.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.57.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.57.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.58.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.58.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.58.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.59.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.59.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.59.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.6.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.6.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.6.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.60.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.60.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.60.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.61.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.61.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.61.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.62.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.62.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.62.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.63.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.63.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.63.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.64.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.64.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.64.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.65.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.65.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.65.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.66.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.66.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.66.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.67.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.67.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.67.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.68.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.68.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.68.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.69.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.69.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.69.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.7.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.7.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.7.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.70.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.70.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.70.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.71.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.71.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.71.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.72.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.72.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.72.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.73.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.73.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.73.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.74.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.74.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.74.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.75.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.75.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.75.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.76.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.76.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.76.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.77.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.77.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.77.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.78.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.78.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.78.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.79.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.79.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.79.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.8.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.8.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.8.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.80.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.80.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.80.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.81.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.81.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.81.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.82.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.82.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.82.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.83.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.83.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.83.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.84.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.84.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.84.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.85.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.85.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.85.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.86.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.86.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.86.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.87.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.87.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.87.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.88.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.88.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.88.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.89.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.89.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.89.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.9.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.9.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.9.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.90.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.90.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.90.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.91.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.91.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.91.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.92.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.92.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.92.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.93.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.93.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.93.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.94.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.94.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.94.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.95.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.95.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.95.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.96.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.96.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.96.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.97.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.97.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.97.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.98.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.98.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.98.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.99.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.99.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.experts.99.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.gate.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00020-of-00033.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.A_log": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.dt_bias": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.norm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.0.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.0.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.0.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.1.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.1.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.1.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.10.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.10.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.10.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.100.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.100.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.100.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.101.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.101.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.101.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.102.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.102.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.102.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.103.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.103.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.103.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.104.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.104.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.104.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.105.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.105.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.105.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.106.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.106.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.106.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.107.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.107.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.107.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.108.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.108.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.108.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.109.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.109.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.109.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.11.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.11.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.11.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.110.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.110.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.110.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.111.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.111.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.111.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.112.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.112.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.112.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.113.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.113.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.113.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.114.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.114.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.114.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.115.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.115.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.115.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.116.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.116.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.116.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.117.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.117.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.117.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.118.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.118.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.118.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.119.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.119.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.119.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.12.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.12.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.12.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.120.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.120.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.120.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.121.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.121.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.121.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.122.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.122.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.122.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.123.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.123.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.123.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.124.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.124.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.124.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.125.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.125.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.125.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.126.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.126.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.126.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.127.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.127.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.127.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.128.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.128.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.128.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.129.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.129.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.129.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.13.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.13.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.13.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.130.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.130.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.130.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.131.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.131.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.131.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.132.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.132.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.132.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.133.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.133.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.133.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.134.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.134.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.134.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.135.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.135.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.135.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.136.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.136.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.136.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.137.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.137.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.137.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.138.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.138.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.138.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.139.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.139.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.139.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.14.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.14.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.14.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.140.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.140.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.140.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.141.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.141.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.141.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.142.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.142.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.142.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.143.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.143.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.143.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.144.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.144.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.144.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.145.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.145.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.145.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.146.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.146.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.146.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.147.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.147.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.147.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.148.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.148.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.148.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.149.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.149.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.149.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.15.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.15.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.15.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.150.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.150.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.150.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.151.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.151.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.151.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.152.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.152.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.152.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.153.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.153.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.153.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.154.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.154.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.154.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.155.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.155.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.155.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.156.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.156.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.156.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.157.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.157.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.157.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.158.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.158.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.158.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.159.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.159.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.159.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.16.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.16.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.16.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.160.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.160.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.160.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.161.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.161.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.161.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.162.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.162.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.162.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.163.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.163.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.163.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.164.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.164.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.164.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.165.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.165.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.165.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.166.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.166.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.166.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.167.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.167.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.167.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.168.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.168.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.168.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.169.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.169.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.169.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.17.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.17.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.17.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.170.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.170.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.170.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.171.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.171.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.171.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.172.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.172.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.172.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.173.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.173.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.173.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.174.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.174.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.174.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.175.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.175.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.175.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.176.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.176.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.176.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.177.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.177.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.177.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.178.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.178.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.178.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.179.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.179.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.179.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.18.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.18.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.18.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.180.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.180.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.180.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.181.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.181.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.181.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.182.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.182.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.182.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.183.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.183.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.183.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.184.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.184.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.184.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.185.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.185.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.185.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.186.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.186.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.186.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.187.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.187.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.187.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.188.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.188.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.188.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.189.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.189.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.189.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.19.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.19.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.19.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.190.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.190.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.190.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.191.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.191.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.191.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.192.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.192.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.192.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.193.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.193.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.193.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.194.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.194.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.194.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.195.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.195.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.195.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.196.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.196.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.196.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.197.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.197.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.197.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.198.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.198.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.198.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.199.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.199.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.199.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.2.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.2.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.2.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.20.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.20.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.20.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.200.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.200.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.200.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.201.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.201.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.201.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.202.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.202.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.202.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.203.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.203.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.203.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.204.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.204.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.204.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.205.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.205.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.205.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.206.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.206.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.206.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.207.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.207.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.207.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.208.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.208.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.208.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.209.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.209.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.209.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.21.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.21.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.21.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.210.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.210.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.210.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.211.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.211.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.211.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.212.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.212.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.212.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.213.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.213.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.213.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.214.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.214.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.214.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.215.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.215.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.215.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.216.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.216.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.216.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.217.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.217.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.217.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.218.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.218.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.218.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.219.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.219.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.219.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.22.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.22.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.22.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.220.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.220.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.220.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.221.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.221.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.221.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.222.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.222.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.222.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.223.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.223.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.223.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.224.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.224.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.224.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.225.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.225.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.225.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.226.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.226.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.226.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.227.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.227.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.227.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.228.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.228.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.228.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.229.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.229.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.229.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.23.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.23.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.23.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.230.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.230.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.230.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.231.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.231.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.231.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.232.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.232.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.232.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.233.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.233.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.233.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.234.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.234.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.234.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.235.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.235.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.235.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.236.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.236.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.236.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.237.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.237.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.237.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.238.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.238.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.238.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.239.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.239.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.239.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.24.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.24.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.24.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.240.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.240.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.240.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.241.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.241.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.241.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.242.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.242.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.242.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.243.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.243.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.243.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.244.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.244.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.244.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.245.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.245.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.245.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.246.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.246.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.246.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.247.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.247.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.247.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.248.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.248.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.248.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.249.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.249.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.249.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.25.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.25.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.25.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.250.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.250.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.250.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.251.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.251.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.251.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.252.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.252.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.252.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.253.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.253.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.253.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.254.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.254.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.254.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.255.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.255.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.255.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.26.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.26.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.26.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.27.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.27.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.27.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.28.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.28.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.28.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.29.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.29.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.29.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.3.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.3.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.3.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.30.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.30.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.30.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.31.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.31.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.31.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.32.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.32.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.32.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.33.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.33.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.33.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.34.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.34.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.34.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.35.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.35.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.35.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.36.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.36.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.36.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.37.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.37.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.37.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.38.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.38.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.38.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.39.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.39.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.39.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.4.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.4.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.4.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.40.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.40.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.40.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.41.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.41.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.41.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.42.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.42.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.42.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.43.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.43.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.43.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.44.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.44.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.44.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.45.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.45.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.45.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.46.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.46.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.46.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.47.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.47.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.47.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.48.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.48.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.48.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.49.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.49.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.49.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.5.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.5.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.5.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.50.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.50.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.50.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.51.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.51.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.51.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.52.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.52.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.52.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.53.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.53.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.53.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.54.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.54.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.54.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.55.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.55.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.55.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.56.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.56.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.56.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.57.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.57.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.57.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.58.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.58.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.58.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.59.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.59.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.59.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.6.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.6.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.6.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.60.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.60.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.60.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.61.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.61.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.61.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.62.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.62.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.62.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.63.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.63.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.63.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.64.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.64.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.64.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.65.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.65.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.65.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.66.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.66.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.66.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.67.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.67.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.67.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.68.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.68.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.68.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.69.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.69.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.69.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.7.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.7.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.7.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.70.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.70.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.70.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.71.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.71.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.71.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.72.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.72.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.72.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.73.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.73.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.73.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.74.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.74.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.74.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.75.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.75.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.75.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.76.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.76.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.76.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.77.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.77.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.77.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.78.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.78.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.78.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.79.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.79.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.79.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.8.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.8.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.8.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.80.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.80.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.80.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.81.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.81.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.81.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.82.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.82.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.82.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.83.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.83.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.83.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.84.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.84.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.84.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.85.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.85.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.85.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.86.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.86.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.86.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.87.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.87.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.87.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.88.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.88.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.88.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.89.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.89.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.89.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.9.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.9.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.9.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.90.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.90.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.90.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.91.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.91.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.91.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.92.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.92.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.92.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.93.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.93.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.93.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.94.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.94.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.94.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.95.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.95.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.95.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.96.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.96.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.96.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.97.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.97.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.97.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.98.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.98.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.98.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.99.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.99.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.experts.99.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.gate.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.A_log": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.dt_bias": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.norm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.0.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.0.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.0.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.1.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.1.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.1.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.10.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.10.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.10.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.100.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.100.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.100.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.101.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.101.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.101.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.102.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.102.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.102.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.103.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.103.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.103.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.104.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.104.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.104.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.105.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.105.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.105.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.106.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.106.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.106.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.107.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.107.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.107.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.108.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.108.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.108.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.109.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.109.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.109.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.11.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.11.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.11.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.110.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.110.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.110.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.111.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.111.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.111.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.112.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.112.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.112.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.113.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.113.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.113.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.114.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.114.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.114.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.115.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.115.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.115.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.116.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.116.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.116.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.117.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.117.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.117.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.118.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.118.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.118.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.119.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.119.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.119.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.12.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.12.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.12.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.120.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.120.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.120.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.121.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.121.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.121.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.122.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.122.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.122.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.123.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.123.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.123.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.124.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.124.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.124.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.125.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.125.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.125.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.126.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.126.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.126.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.127.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.127.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.127.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.128.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.128.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.128.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.129.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.129.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.129.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.13.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.13.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.13.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.130.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.130.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.130.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.131.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.131.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.131.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.132.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.132.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.132.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.133.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.133.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.133.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.134.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.134.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.134.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.135.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.135.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.135.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.136.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.136.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.136.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.137.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.137.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.137.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.138.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.138.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.138.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.139.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.139.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.139.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.14.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.14.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.14.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.140.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.140.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.140.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.141.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.141.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.141.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.142.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.142.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.142.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.143.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.143.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.143.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.144.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.144.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.144.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.145.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.145.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.145.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.146.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.146.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.146.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.147.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.147.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.147.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.148.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.148.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.148.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.149.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.149.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.149.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.15.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.15.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.15.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.150.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.150.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.150.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.151.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.151.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.151.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.152.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.152.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.152.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.153.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.153.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.153.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.154.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.154.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.154.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.155.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.155.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.155.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.156.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.156.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.156.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.157.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.157.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.157.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.158.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.158.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.158.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.159.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.159.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.159.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.16.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.16.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.16.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.160.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.160.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.160.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.161.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.161.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.161.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.162.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.162.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.162.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.163.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.163.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.163.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.164.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.164.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.164.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.165.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.165.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.165.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.166.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.166.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.166.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.167.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.167.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.167.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.168.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.168.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.168.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.169.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.169.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.169.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.17.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.17.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.17.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.170.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.170.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.170.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.171.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.171.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.171.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.172.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.172.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.172.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.173.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.173.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.173.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.174.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.174.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.174.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.175.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.175.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.175.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.176.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.176.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.176.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.177.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.177.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.177.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.178.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.178.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.178.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.179.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.179.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.179.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.18.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.18.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.18.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.180.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.180.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.180.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.181.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.181.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.181.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.182.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.182.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.182.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.183.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.183.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.183.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.184.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.184.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.184.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.185.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.185.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.185.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.186.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.186.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.186.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.187.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.187.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.187.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.188.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.188.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.188.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.189.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.189.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.189.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.19.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.19.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.19.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.190.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.190.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.190.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.191.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.191.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.191.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.192.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.192.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.192.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.193.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.193.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.193.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.194.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.194.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.194.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.195.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.195.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.195.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.196.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.196.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.196.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.197.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.197.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.197.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.198.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.198.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.198.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.199.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.199.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.199.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.2.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.2.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.2.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.20.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.20.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.20.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.200.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.200.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.200.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.201.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.201.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.201.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.202.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.202.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.202.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.203.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.203.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.203.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.204.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.204.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.204.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.205.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.205.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.205.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.206.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.206.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.206.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.207.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.207.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.207.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.208.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.208.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.208.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.209.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.209.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.209.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.21.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.21.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.21.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.210.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.210.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.210.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.211.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.211.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.211.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.212.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.212.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.212.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.213.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.213.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.213.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.214.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.214.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.214.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.215.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.215.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.215.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.216.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.216.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.216.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.217.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.217.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.217.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.218.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.218.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.218.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.219.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.219.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.219.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.22.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.22.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.22.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.220.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.220.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.220.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.221.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.221.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.221.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.222.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.222.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.222.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.223.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.223.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.223.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.224.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.224.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.224.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.225.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.225.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.225.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.226.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.226.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.226.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.227.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.227.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.227.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.228.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.228.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.228.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.229.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.229.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.229.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.23.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.23.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.23.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.230.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.230.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.230.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.231.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.231.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.231.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.232.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.232.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.232.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.233.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.233.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.233.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.234.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.234.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.234.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.235.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.235.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.235.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.236.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.236.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.236.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.237.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.237.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.237.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.238.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.238.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.238.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.239.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.239.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.239.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.24.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.24.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.24.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.240.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.240.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.240.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.241.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.241.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.241.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.242.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.242.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.242.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.243.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.243.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.243.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.244.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.244.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.244.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.245.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.245.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.245.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.246.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.246.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.246.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.247.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.247.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.247.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.248.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.248.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.248.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.249.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.249.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.249.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.25.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.25.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.25.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.250.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.250.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.250.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.251.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.251.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.251.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.252.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.252.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.252.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.253.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.253.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.253.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.254.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.254.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.254.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.255.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.255.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.255.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.26.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.26.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.26.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.27.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.27.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.27.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.28.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.28.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.28.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.29.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.29.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.29.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.3.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.3.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.3.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.30.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.30.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.30.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.31.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.31.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.31.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.32.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.32.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.32.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.33.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.33.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.33.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.34.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.34.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.34.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.35.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.35.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.35.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.36.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.36.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.36.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.37.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.37.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.37.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.38.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.38.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.38.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.39.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.39.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.39.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.4.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.4.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.4.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.40.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.40.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.40.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.41.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.41.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.41.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.42.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.42.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.42.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.43.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.43.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.43.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.44.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.44.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.44.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.45.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.45.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.45.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.46.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.46.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.46.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.47.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.47.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.47.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.48.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.48.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.48.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.49.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.49.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.49.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.5.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.5.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.5.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.50.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.50.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.50.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.51.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.51.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.51.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.52.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.52.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.52.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.53.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.53.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.53.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.54.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.54.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.54.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.55.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.55.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.55.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.56.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.56.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.56.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.57.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.57.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.57.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.58.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.58.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.58.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.59.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.59.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.59.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.6.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.6.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.6.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.60.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.60.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.60.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.61.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.61.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.61.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.62.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.62.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.62.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.63.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.63.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.63.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.64.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.64.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.64.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.65.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.65.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.65.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.66.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.66.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.66.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.67.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.67.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.67.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.68.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.68.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.68.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.69.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.69.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.69.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.7.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.7.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.7.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.70.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.70.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.70.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.71.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.71.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.71.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.72.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.72.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.72.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.73.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.73.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.73.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.74.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.74.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.74.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.75.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.75.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.75.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.76.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.76.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.76.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.77.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.77.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.77.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.78.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.78.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.78.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.79.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.79.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.79.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.8.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.8.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.8.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.80.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.80.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.80.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.81.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.81.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.81.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.82.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.82.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.82.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.83.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.83.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.83.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.84.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.84.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.84.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.85.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.85.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.85.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.86.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.86.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.86.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.87.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.87.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.87.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.88.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.88.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.88.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.89.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.89.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.89.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.9.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.9.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.9.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.90.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.90.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.90.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.91.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.91.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.91.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.92.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.92.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.92.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.93.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.93.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.93.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.94.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.94.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.94.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.95.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.95.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.95.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.96.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.96.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.96.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.97.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.97.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.97.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.98.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.98.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.98.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.99.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.99.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.experts.99.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.26.mlp.gate.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.0.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.0.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.0.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.1.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.1.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.1.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.10.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.10.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.10.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.100.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.100.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.100.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.101.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.101.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.101.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.102.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.102.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.102.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.103.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.103.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.103.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.104.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.104.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.104.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.105.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.105.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.105.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.106.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.106.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.106.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.107.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.107.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.107.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.108.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.108.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.108.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.109.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.109.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.109.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.11.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.11.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.11.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.110.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.110.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.110.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.111.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.111.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.111.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.112.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.112.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.112.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.113.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.113.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.113.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.114.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.114.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.114.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.115.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.115.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.115.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.116.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.116.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.116.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.117.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.117.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.117.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.118.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.118.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.118.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.119.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.119.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.119.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.12.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.12.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.12.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.120.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.120.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.120.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.121.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.121.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.121.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.122.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.122.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.122.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.123.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.123.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.123.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.124.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.124.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.124.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.125.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.125.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.125.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.126.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.126.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.126.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.127.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.127.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.127.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.128.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.128.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.128.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.129.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.129.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.129.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.13.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.13.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.13.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.130.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.130.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.130.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.131.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.131.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.131.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.132.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.132.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.132.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.133.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.133.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.133.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.134.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.134.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.134.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.135.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.135.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.135.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.136.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.136.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.136.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.137.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.137.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.137.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.138.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.138.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.138.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.139.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.139.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.139.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.14.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.14.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.14.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.140.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.140.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.140.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.141.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.141.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.141.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.142.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.142.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.142.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.143.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.143.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.143.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.144.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.144.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.144.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.145.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.145.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.145.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.146.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.146.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.146.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.147.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.147.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.147.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.148.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.148.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.148.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.149.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.149.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.149.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.15.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.15.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.15.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.150.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.150.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.150.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.151.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.151.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.151.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.152.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.152.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.152.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.153.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.153.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.153.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.154.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.154.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.154.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.155.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.155.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.155.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.156.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.156.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.156.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.157.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.157.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.157.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.158.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.158.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.158.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.159.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.159.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.159.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.16.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.16.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.16.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.160.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.160.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.160.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.161.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.161.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.161.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.162.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.162.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.162.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.163.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.163.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.163.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.164.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.164.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.164.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.165.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.165.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.165.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.166.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.166.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.166.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.167.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.167.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.167.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.168.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.168.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.168.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.169.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.169.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.169.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.17.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.17.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.17.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.170.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.170.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.170.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.171.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.171.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.171.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.172.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.172.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.172.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.173.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.173.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.173.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.174.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.174.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.174.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.175.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.175.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.175.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.176.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.176.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.176.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.177.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.177.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.177.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.178.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.178.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.178.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.179.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.179.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.179.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.18.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.18.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.18.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.180.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.180.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.180.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.181.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.181.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.181.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.182.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.182.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.182.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.183.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.183.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.183.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.184.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.184.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.184.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.185.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.185.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.185.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.186.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.186.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.186.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.187.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.187.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.187.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.188.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.188.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.188.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.189.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.189.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.189.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.19.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.19.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.19.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.190.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.190.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.190.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.191.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.191.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.191.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.192.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.192.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.192.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.193.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.193.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.193.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.194.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.194.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.194.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.195.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.195.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.195.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.196.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.196.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.196.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.197.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.197.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.197.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.198.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.198.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.198.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.199.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.199.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.199.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.2.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.2.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.2.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.20.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.20.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.20.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.200.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.200.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.200.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.201.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.201.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.201.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.202.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.202.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.202.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.203.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.203.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.203.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.204.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.204.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.204.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.205.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.205.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.205.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.206.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.206.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.206.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.207.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.207.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.207.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.208.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.208.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.208.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.209.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.209.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.209.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.21.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.21.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.21.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.210.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.210.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.210.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.211.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.211.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.211.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.212.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.212.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.212.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.213.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.213.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.213.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.214.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.214.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.214.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.215.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.215.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.215.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.216.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.216.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.216.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.217.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.217.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.217.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.218.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.218.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.218.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.219.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.219.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.219.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.22.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.22.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.22.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.220.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.220.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.220.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.221.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.221.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.221.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.222.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.222.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.222.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.223.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.223.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.223.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.224.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.224.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.224.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.225.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.225.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.225.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.226.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.226.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.226.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.227.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.227.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.227.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.228.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.228.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.228.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.229.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.229.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.229.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.23.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.23.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.23.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.230.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.230.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.230.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.231.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.231.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.231.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.232.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.232.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.232.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.233.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.233.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.233.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.234.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.234.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.234.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.235.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.235.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.235.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.236.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.236.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.236.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.237.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.237.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.237.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.238.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.238.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.238.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.239.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.239.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.239.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.24.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.24.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.24.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.240.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.240.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.240.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.241.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.241.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.241.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.242.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.242.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.242.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.243.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.243.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.243.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.244.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.244.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.244.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.245.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.245.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.245.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.246.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.246.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.246.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.247.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.247.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.247.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.248.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.248.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.248.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.249.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.249.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.249.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.25.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.25.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.25.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.250.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.250.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.250.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.251.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.251.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.251.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.252.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.252.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.252.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.253.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.253.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.253.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.254.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.254.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.254.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.255.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.255.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.255.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.26.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.26.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.26.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.27.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.27.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.27.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.28.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.28.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.28.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.29.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.29.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.29.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.3.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.3.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.3.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.30.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.30.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.30.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.31.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.31.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.31.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.32.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.32.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.32.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.33.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.33.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.33.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.34.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.34.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.34.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.35.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.35.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.35.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.36.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.36.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.36.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.37.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.37.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.37.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.38.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.38.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.38.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.39.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.39.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.39.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.4.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.4.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.4.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.40.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.40.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.40.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.41.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.41.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.41.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.42.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.42.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.42.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.43.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.43.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.43.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.44.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.44.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.44.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.45.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.45.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.45.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.46.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.46.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.46.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.47.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.47.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.47.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.48.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.48.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.48.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.49.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.49.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.49.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.5.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.5.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.5.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.50.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.50.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.50.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.51.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.51.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.51.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.52.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.52.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.52.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.53.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.53.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.53.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.54.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.54.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.54.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.55.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.55.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.55.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.56.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.56.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.56.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.57.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.57.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.57.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.58.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.58.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.58.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.59.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.59.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.59.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.6.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.6.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.6.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.60.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.60.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.60.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.61.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.61.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.61.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.62.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.62.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.62.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.63.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.63.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.63.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.64.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.64.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.64.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.65.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.65.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.65.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.66.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.66.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.66.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.67.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.67.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.67.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.68.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.68.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.68.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.69.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.69.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.69.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.7.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.7.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.7.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.70.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.70.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.70.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.71.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.71.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.71.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.72.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.72.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.72.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.73.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.73.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.73.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.74.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.74.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.74.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.75.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.75.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.75.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.76.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.76.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.76.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.77.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.77.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.77.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.78.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.78.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.78.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.79.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.79.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.79.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.8.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.8.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.8.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.80.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.80.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.80.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.81.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.81.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.81.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.82.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.82.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.82.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.83.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.83.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.83.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.84.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.84.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.84.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.85.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.85.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.85.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.86.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.86.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.86.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.87.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.87.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.87.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.88.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.88.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.88.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.89.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.89.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.89.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.9.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.9.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.9.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.90.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.90.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.90.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.91.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.91.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.91.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.92.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.92.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.92.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.93.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.93.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.93.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.94.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.94.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.94.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.95.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.95.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.95.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.96.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.96.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.96.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.97.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.97.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.97.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.98.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.98.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.98.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.99.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.99.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.experts.99.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.gate.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00022-of-00033.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.A_log": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.dt_bias": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.norm.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.0.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.0.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.0.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.1.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.1.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.1.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.10.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.10.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.10.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.100.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.100.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.100.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.101.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.101.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.101.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.102.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.102.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.102.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.103.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.103.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.103.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.104.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.104.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.104.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.105.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.105.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.105.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.106.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.106.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.106.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.107.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.107.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.107.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.108.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.108.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.108.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.109.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.109.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.109.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.11.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.11.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.11.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.110.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.110.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.110.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.111.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.111.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.111.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.112.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.112.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.112.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.113.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.113.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.113.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.114.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.114.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.114.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.115.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.115.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.115.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.116.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.116.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.116.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.117.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.117.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.117.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.118.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.118.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.118.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.119.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.119.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.119.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.12.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.12.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.12.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.120.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.120.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.120.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.121.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.121.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.121.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.122.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.122.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.122.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.123.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.123.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.123.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.124.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.124.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.124.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.125.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.125.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.125.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.126.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.126.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.126.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.127.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.127.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.127.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.128.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.128.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.128.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.129.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.129.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.129.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.13.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.13.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.13.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.130.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.130.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.130.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.131.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.131.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.131.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.132.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.132.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.132.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.133.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.133.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.133.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.134.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.134.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.134.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.135.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.135.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.135.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.136.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.136.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.136.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.137.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.137.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.137.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.138.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.138.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.138.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.139.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.139.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.139.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.14.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.14.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.14.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.140.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.140.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.140.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.141.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.141.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.141.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.142.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.142.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.142.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.143.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.143.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.143.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.144.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.144.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.144.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.145.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.145.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.145.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.146.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.146.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.146.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.147.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.147.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.147.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.148.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.148.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.148.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.149.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.149.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.149.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.15.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.15.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.15.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.150.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.150.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.150.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.151.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.151.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.151.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.152.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.152.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.152.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.153.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.153.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.153.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.154.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.154.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.154.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.155.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.155.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.155.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.156.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.156.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.156.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.157.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.157.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.157.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.158.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.158.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.158.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.159.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.159.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.159.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.16.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.16.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.16.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.160.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.160.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.160.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.161.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.161.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.161.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.162.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.162.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.162.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.163.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.163.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.163.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.164.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.164.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.164.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.165.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.165.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.165.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.166.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.166.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.166.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.167.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.167.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.167.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.168.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.168.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.168.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.169.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.169.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.169.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.17.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.17.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.17.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.170.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.170.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.170.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.171.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.171.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.171.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.172.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.172.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.172.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.173.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.173.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.173.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.174.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.174.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.174.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.175.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.175.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.175.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.176.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.176.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.176.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.177.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.177.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.177.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.178.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.178.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.178.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.179.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.179.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.179.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.18.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.18.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.18.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.180.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.180.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.180.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.181.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.181.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.181.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.182.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.182.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.182.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.183.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.183.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.183.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.184.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.184.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.184.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.185.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.185.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.185.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.186.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.186.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.186.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.187.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.187.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.187.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.188.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.188.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.188.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.189.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.189.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.189.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.19.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.19.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.19.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.190.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.190.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.190.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.191.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.191.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.191.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.192.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.192.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.192.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.193.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.193.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.193.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.194.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.194.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.194.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.195.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.195.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.195.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.196.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.196.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.196.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.197.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.197.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.197.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.198.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.198.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.198.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.199.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.199.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.199.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.2.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.2.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.2.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.20.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.20.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.20.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.200.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.200.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.200.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.201.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.201.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.201.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.202.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.202.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.202.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.203.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.203.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.203.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.204.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.204.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.204.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.205.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.205.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.205.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.206.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.206.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.206.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.207.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.207.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.207.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.208.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.208.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.208.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.209.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.209.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.209.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.21.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.21.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.21.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.210.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.210.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.210.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.211.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.211.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.211.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.212.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.212.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.212.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.213.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.213.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.213.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.214.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.214.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.214.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.215.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.215.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.215.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.216.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.216.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.216.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.217.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.217.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.217.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.218.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.218.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.218.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.219.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.219.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.219.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.22.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.22.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.22.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.220.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.220.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.220.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.221.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.221.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.221.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.222.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.222.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.222.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.223.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.223.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.223.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.224.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.224.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.224.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.225.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.225.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.225.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.226.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.226.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.226.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.227.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.227.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.227.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.228.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.228.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.228.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.229.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.229.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.229.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.23.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.23.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.23.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.230.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.230.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.230.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.231.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.231.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.231.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.232.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.232.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.232.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.233.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.233.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.233.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.234.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.234.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.234.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.235.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.235.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.235.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.236.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.236.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.236.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.237.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.237.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.237.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.238.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.238.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.238.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.239.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.239.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.239.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.24.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.24.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.24.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.240.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.240.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.240.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.241.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.241.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.241.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.242.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.242.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.242.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.243.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.243.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.243.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.244.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.244.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.244.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.245.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.245.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.245.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.246.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.246.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.246.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.247.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.247.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.247.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.248.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.248.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.248.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.249.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.249.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.249.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.25.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.25.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.25.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.250.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.250.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.250.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.251.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.251.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.251.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.252.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.252.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.252.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.253.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.253.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.253.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.254.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.254.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.254.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.255.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.255.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.255.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.26.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.26.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.26.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.27.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.27.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.27.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.28.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.28.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.28.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.29.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.29.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.29.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.3.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.3.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.3.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.30.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.30.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.30.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.31.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.31.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.31.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.32.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.32.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.32.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.33.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.33.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.33.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.34.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.34.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.34.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.35.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.35.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.35.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.36.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.36.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.36.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.37.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.37.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.37.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.38.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.38.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.38.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.39.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.39.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.39.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.4.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.4.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.4.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.40.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.40.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.40.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.41.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.41.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.41.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.42.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.42.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.42.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.43.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.43.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.43.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.44.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.44.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.44.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.45.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.45.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.45.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.46.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.46.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.46.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.47.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.47.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.47.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.48.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.48.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.48.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.49.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.49.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.49.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.5.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.5.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.5.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.50.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.50.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.50.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.51.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.51.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.51.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.52.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.52.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.52.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.53.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.53.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.53.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.54.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.54.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.54.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.55.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.55.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.55.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.56.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.56.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.56.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.57.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.57.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.57.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.58.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.58.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.58.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.59.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.59.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.59.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.6.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.6.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.6.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.60.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.60.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.60.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.61.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.61.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.61.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.62.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.62.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.62.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.63.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.63.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.63.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.64.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.64.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.64.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.65.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.65.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.65.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.66.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.66.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.66.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.67.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.67.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.67.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.68.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.68.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.68.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.69.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.69.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.69.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.7.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.7.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.7.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.70.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.70.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.70.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.71.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.71.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.71.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.72.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.72.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.72.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.73.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.73.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.73.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.74.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.74.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.74.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.75.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.75.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.75.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.76.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.76.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.76.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.77.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.77.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.77.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.78.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.78.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.78.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.79.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.79.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.79.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.8.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.8.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.8.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.80.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.80.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.80.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.81.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.81.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.81.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.82.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.82.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.82.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.83.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.83.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.83.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.84.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.84.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.84.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.85.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.85.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.85.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.86.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.86.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.86.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.87.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.87.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.87.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.88.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.88.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.88.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.89.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.89.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.89.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.9.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.9.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.9.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.90.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.90.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.90.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.91.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.91.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.91.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.92.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.92.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.92.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.93.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.93.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.93.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.94.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.94.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.94.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.95.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.95.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.95.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.96.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.96.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.96.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.97.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.97.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.97.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.98.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.98.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.98.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.99.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.99.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.experts.99.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.gate.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00023-of-00033.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.A_log": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.dt_bias": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.norm.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.0.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.0.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.0.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.1.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.1.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.1.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.10.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.10.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.10.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.100.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.100.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.100.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.101.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.101.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.101.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.102.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.102.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.102.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.103.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.103.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.103.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.104.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.104.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.104.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.105.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.105.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.105.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.106.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.106.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.106.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.107.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.107.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.107.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.108.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.108.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.108.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.109.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.109.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.109.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.11.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.11.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.11.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.110.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.110.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.110.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.111.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.111.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.111.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.112.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.112.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.112.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.113.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.113.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.113.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.114.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.114.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.114.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.115.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.115.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.115.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.116.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.116.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.116.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.117.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.117.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.117.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.118.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.118.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.118.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.119.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.119.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.119.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.12.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.12.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.12.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.120.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.120.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.120.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.121.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.121.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.121.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.122.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.122.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.122.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.123.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.123.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.123.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.124.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.124.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.124.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.125.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.125.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.125.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.126.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.126.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.126.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.127.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.127.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.127.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.128.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.128.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.128.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.129.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.129.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.129.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.13.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.13.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.13.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.130.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.130.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.130.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.131.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.131.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.131.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.132.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.132.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.132.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.133.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.133.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.133.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.134.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.134.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.134.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.135.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.135.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.135.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.136.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.136.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.136.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.137.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.137.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.137.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.138.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.138.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.138.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.139.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.139.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.139.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.14.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.14.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.14.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.140.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.140.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.140.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.141.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.141.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.141.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.142.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.142.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.142.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.143.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.143.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.143.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.144.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.144.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.144.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.145.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.145.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.145.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.146.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.146.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.146.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.147.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.147.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.147.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.148.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.148.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.148.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.149.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.149.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.149.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.15.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.15.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.15.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.150.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.150.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.150.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.151.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.151.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.151.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.152.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.152.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.152.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.153.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.153.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.153.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.154.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.154.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.154.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.155.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.155.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.155.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.156.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.156.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.156.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.157.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.157.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.157.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.158.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.158.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.158.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.159.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.159.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.159.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.16.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.16.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.16.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.160.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.160.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.160.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.161.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.161.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.161.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.162.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.162.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.162.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.163.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.163.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.163.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.164.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.164.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.164.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.165.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.165.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.165.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.166.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.166.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.166.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.167.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.167.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.167.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.168.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.168.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.168.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.169.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.169.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.169.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.17.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.17.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.17.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.170.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.170.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.170.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.171.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.171.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.171.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.172.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.172.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.172.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.173.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.173.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.173.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.174.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.174.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.174.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.175.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.175.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.175.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.176.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.176.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.176.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.177.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.177.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.177.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.178.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.178.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.178.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.179.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.179.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.179.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.18.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.18.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.18.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.180.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.180.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.180.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.181.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.181.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.181.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.182.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.182.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.182.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.183.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.183.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.183.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.184.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.184.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.184.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.185.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.185.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.185.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.186.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.186.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.186.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.187.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.187.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.187.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.188.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.188.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.188.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.189.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.189.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.189.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.19.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.19.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.19.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.190.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.190.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.190.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.191.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.191.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.191.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.192.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.192.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.192.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.193.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.193.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.193.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.194.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.194.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.194.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.195.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.195.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.195.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.196.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.196.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.196.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.197.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.197.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.197.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.198.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.198.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.198.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.199.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.199.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.199.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.2.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.2.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.2.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.20.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.20.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.20.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.200.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.200.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.200.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.201.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.201.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.201.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.202.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.202.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.202.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.203.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.203.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.203.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.204.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.204.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.204.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.205.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.205.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.205.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.206.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.206.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.206.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.207.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.207.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.207.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.208.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.208.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.208.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.209.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.209.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.209.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.21.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.21.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.21.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.210.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.210.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.210.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.211.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.211.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.211.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.212.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.212.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.212.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.213.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.213.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.213.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.214.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.214.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.214.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.215.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.215.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.215.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.216.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.216.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.216.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.217.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.217.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.217.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.218.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.218.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.218.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.219.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.219.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.219.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.22.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.22.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.22.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.220.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.220.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.220.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.221.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.221.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.221.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.222.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.222.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.222.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.223.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.223.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.223.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.224.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.224.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.224.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.225.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.225.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.225.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.226.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.226.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.226.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.227.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.227.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.227.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.228.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.228.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.228.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.229.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.229.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.229.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.23.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.23.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.23.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.230.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.230.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.230.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.231.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.231.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.231.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.232.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.232.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.232.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.233.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.233.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.233.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.234.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.234.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.234.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.235.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.235.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.235.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.236.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.236.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.236.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.237.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.237.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.237.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.238.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.238.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.238.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.239.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.239.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.239.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.24.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.24.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.24.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.240.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.240.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.240.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.241.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.241.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.241.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.242.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.242.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.242.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.243.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.243.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.243.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.244.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.244.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.244.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.245.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.245.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.245.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.246.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.246.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.246.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.247.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.247.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.247.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.248.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.248.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.248.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.249.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.249.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.249.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.25.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.25.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.25.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.250.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.250.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.250.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.251.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.251.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.251.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.252.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.252.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.252.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.253.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.253.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.253.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.254.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.254.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.254.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.255.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.255.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.255.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.26.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.26.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.26.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.27.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.27.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.27.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.28.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.28.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.28.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.29.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.29.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.29.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.3.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.3.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.3.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.30.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.30.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.30.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.31.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.31.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.31.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.32.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.32.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.32.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.33.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.33.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.33.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.34.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.34.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.34.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.35.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.35.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.35.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.36.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.36.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.36.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.37.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.37.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.37.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.38.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.38.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.38.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.39.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.39.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.39.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.4.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.4.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.4.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.40.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.40.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.40.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.41.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.41.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.41.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.42.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.42.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.42.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.43.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.43.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.43.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.44.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.44.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.44.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.45.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.45.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.45.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.46.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.46.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.46.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.47.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.47.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.47.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.48.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.48.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.48.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.49.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.49.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.49.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.5.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.5.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.5.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.50.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.50.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.50.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.51.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.51.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.51.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.52.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.52.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.52.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.53.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.53.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.53.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.54.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.54.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.54.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.55.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.55.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.55.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.56.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.56.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.56.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.57.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.57.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.57.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.58.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.58.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.58.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.59.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.59.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.59.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.6.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.6.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.6.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.60.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.60.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.60.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.61.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.61.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.61.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.62.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.62.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.62.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.63.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.63.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.63.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.64.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.64.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.64.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.65.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.65.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.65.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.66.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.66.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.66.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.67.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.67.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.67.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.68.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.68.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.68.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.69.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.69.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.69.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.7.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.7.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.7.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.70.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.70.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.70.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.71.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.71.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.71.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.72.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.72.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.72.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.73.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.73.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.73.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.74.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.74.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.74.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.75.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.75.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.75.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.76.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.76.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.76.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.77.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.77.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.77.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.78.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.78.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.78.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.79.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.79.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.79.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.8.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.8.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.8.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.80.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.80.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.80.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.81.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.81.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.81.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.82.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.82.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.82.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.83.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.83.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.83.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.84.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.84.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.84.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.85.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.85.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.85.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.86.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.86.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.86.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.87.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.87.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.87.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.88.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.88.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.88.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.89.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.89.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.89.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.9.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.9.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.9.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.90.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.90.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.90.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.91.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.91.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.91.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.92.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.92.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.92.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.93.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.93.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.93.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.94.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.94.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.94.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.95.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.95.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.95.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.96.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.96.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.96.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.97.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.97.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.97.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.98.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.98.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.98.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.99.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.99.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.experts.99.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.gate.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.0.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.0.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.1.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.10.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.10.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.100.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.100.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.100.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.101.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.101.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.101.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.102.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.102.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.102.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.103.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.103.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.103.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.104.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.104.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.104.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.105.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.105.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.105.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.106.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.107.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.108.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.109.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.11.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.11.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.110.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.111.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.112.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.113.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.114.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.115.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.116.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.118.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.119.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.12.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.12.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.120.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.121.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.122.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.123.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.124.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.125.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.126.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.127.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.128.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.128.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.128.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.129.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.129.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.129.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.13.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.13.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.130.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.130.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.130.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.131.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.131.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.131.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.132.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.132.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.132.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.133.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.133.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.133.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.134.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.134.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.134.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.135.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.135.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.135.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.136.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.136.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.136.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.137.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.137.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.137.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.138.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.138.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.138.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.139.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.139.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.139.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.14.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.14.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.140.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.140.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.140.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.141.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.141.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.141.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.142.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.142.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.142.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.143.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.143.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.143.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.144.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.144.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.144.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.145.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.145.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.145.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.146.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.146.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.146.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.147.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.147.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.147.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.148.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.148.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.148.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.149.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.149.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.149.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.15.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.15.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.150.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.150.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.150.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.151.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.151.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.151.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.152.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.152.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.152.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.153.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.153.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.153.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.154.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.154.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.154.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.155.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.155.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.155.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.156.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.156.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.156.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.157.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.157.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.157.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.158.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.158.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.158.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.159.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.159.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.159.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.16.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.16.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.16.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.160.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.160.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.160.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.161.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.161.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.161.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.162.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.162.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.162.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.163.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.163.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.163.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.164.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.164.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.164.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.165.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.165.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.165.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.166.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.166.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.166.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.167.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.167.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.167.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.168.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.168.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.168.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.169.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.169.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.169.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.17.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.17.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.17.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.170.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.170.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.170.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.171.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.171.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.171.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.172.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.172.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.172.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.173.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.173.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.173.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.174.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.174.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.174.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.175.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.175.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.175.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.176.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.176.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.176.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.177.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.177.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.177.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.178.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.178.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.178.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.179.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.179.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.179.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.18.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.18.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.180.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.180.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.180.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.181.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.181.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.181.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.182.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.182.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.182.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.183.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.183.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.183.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.184.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.184.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.184.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.185.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.185.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.185.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.186.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.186.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.186.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.187.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.187.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.187.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.188.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.188.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.188.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.189.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.189.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.189.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.19.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.19.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.19.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.190.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.190.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.190.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.191.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.191.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.191.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.192.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.192.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.192.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.193.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.193.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.193.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.194.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.194.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.194.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.195.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.195.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.195.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.196.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.196.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.196.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.197.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.197.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.197.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.198.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.198.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.198.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.199.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.199.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.199.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.2.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.2.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.20.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.20.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.20.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.200.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.200.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.200.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.201.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.201.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.201.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.202.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.202.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.202.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.203.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.203.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.203.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.204.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.204.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.204.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.205.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.205.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.205.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.206.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.206.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.206.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.207.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.207.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.207.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.208.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.208.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.208.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.209.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.209.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.209.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.21.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.21.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.21.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.210.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.210.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.210.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.211.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.211.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.211.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.212.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.212.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.212.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.213.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.213.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.213.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.214.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.214.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.214.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.215.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.215.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.215.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.216.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.216.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.216.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.217.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.217.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.217.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.218.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.218.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.218.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.219.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.219.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.219.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.22.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.22.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.22.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.220.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.220.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.220.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.221.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.221.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.221.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.222.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.222.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.222.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.223.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.223.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.223.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.224.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.224.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.224.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.225.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.225.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.225.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.226.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.226.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.226.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.227.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.227.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.227.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.228.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.228.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.228.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.229.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.229.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.229.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.23.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.23.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.23.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.230.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.230.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.230.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.231.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.231.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.231.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.232.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.232.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.232.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.233.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.233.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.233.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.234.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.234.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.234.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.235.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.235.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.235.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.236.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.236.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.236.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.237.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.237.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.237.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.238.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.238.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.238.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.239.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.239.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.239.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.24.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.24.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.24.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.240.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.240.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.240.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.241.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.241.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.241.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.242.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.242.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.242.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.243.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.243.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.243.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.244.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.244.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.244.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.245.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.245.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.245.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.246.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.246.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.246.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.247.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.247.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.247.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.248.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.248.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.248.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.249.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.249.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.249.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.25.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.25.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.25.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.250.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.250.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.250.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.251.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.251.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.251.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.252.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.252.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.252.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.253.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.253.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.253.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.254.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.254.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.254.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.255.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.255.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.255.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.26.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.26.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.26.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.27.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.27.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.27.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.28.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.28.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.29.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.29.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.29.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.3.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.3.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.30.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.30.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.30.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.31.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.31.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.31.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.32.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.32.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.33.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.33.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.33.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.34.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.34.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.34.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.35.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.35.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.35.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.36.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.36.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.36.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.37.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.37.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.37.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.38.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.38.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.38.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.39.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.39.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.39.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.4.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.4.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.4.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.40.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.40.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.40.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.41.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.41.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.41.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.42.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.42.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.42.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.43.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.43.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.43.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.44.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.44.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.44.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.45.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.45.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.45.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.46.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.46.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.46.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.47.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.47.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.47.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.48.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.48.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.48.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.49.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.49.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.5.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.5.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.5.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.50.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.50.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.50.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.51.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.51.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.51.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.52.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.52.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.52.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.53.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.53.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.53.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.54.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.54.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.54.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.55.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.55.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.55.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.56.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.56.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.56.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.6.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.6.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.6.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.64.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.64.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.64.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.65.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.65.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.65.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.66.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.66.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.66.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.67.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.67.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.67.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.68.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.68.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.68.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.69.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.69.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.69.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.7.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.7.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.7.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.70.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.70.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.70.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.71.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.71.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.71.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.72.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.72.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.72.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.73.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.73.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.73.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.74.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.74.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.74.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.75.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.75.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.75.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.76.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.76.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.76.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.77.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.77.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.77.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.78.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.78.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.78.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.79.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.79.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.79.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.8.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.8.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.8.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.80.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.80.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.80.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.81.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.81.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.81.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.82.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.82.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.82.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.83.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.83.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.83.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.84.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.84.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.84.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.85.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.85.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.85.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.86.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.86.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.86.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.87.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.87.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.87.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.88.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.88.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.88.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.89.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.89.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.89.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.9.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.9.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.9.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.90.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.90.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.90.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.91.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.91.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.91.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.92.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.92.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.92.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.93.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.93.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.93.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.94.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.94.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.94.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.95.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.95.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.95.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.96.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.96.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.96.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.97.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.97.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.97.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.98.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.98.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.98.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.99.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.99.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.experts.99.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.mlp.gate.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00003-of-00033.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.A_log": "model-00024-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.dt_bias": "model-00024-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00024-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.norm.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.0.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.0.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.0.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.1.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.1.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.1.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.10.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.10.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.10.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.100.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.100.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.100.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.101.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.101.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.101.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.102.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.102.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.102.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.103.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.103.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.103.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.104.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.104.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.104.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.105.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.105.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.105.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.106.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.106.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.106.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.107.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.107.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.107.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.108.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.108.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.108.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.109.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.109.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.109.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.11.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.11.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.11.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.110.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.110.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.110.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.111.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.111.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.111.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.112.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.112.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.112.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.113.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.113.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.113.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.114.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.114.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.114.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.115.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.115.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.115.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.116.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.116.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.116.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.117.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.117.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.117.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.118.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.118.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.118.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.119.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.119.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.119.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.12.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.12.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.12.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.120.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.120.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.120.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.121.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.121.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.121.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.122.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.122.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.122.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.123.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.123.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.123.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.124.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.124.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.124.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.125.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.125.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.125.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.126.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.126.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.126.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.127.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.127.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.127.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.128.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.128.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.128.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.129.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.129.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.129.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.13.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.13.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.13.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.130.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.130.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.130.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.131.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.131.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.131.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.132.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.132.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.132.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.133.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.133.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.133.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.134.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.134.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.134.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.135.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.135.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.135.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.136.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.136.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.136.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.137.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.137.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.137.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.138.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.138.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.138.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.139.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.139.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.139.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.14.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.14.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.14.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.140.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.140.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.140.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.141.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.141.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.141.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.142.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.142.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.142.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.143.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.143.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.143.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.144.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.144.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.144.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.145.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.145.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.145.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.146.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.146.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.146.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.147.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.147.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.147.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.148.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.148.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.148.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.149.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.149.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.149.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.15.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.15.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.15.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.150.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.150.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.150.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.151.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.151.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.151.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.152.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.152.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.152.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.153.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.153.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.153.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.154.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.154.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.154.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.155.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.155.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.155.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.156.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.156.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.156.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.157.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.157.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.157.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.158.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.158.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.158.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.159.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.159.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.159.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.16.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.16.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.16.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.160.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.160.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.160.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.161.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.161.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.161.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.162.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.162.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.162.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.163.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.163.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.163.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.164.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.164.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.164.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.165.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.165.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.165.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.166.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.166.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.166.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.167.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.167.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.167.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.168.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.168.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.168.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.169.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.169.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.169.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.17.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.17.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.17.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.170.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.170.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.170.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.171.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.171.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.171.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.172.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.172.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.172.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.173.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.173.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.173.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.174.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.174.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.174.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.175.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.175.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.175.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.176.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.176.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.176.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.177.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.177.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.177.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.178.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.178.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.178.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.179.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.179.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.179.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.18.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.18.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.18.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.180.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.180.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.180.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.181.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.181.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.181.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.182.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.182.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.182.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.183.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.183.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.183.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.184.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.184.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.184.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.185.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.185.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.185.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.186.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.186.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.186.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.187.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.187.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.187.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.188.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.188.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.188.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.189.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.189.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.189.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.19.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.19.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.19.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.190.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.190.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.190.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.191.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.191.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.191.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.192.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.192.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.192.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.193.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.193.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.193.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.194.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.194.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.194.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.195.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.195.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.195.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.196.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.196.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.196.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.197.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.197.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.197.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.198.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.198.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.198.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.199.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.199.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.199.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.2.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.2.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.2.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.20.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.20.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.20.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.200.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.200.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.200.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.201.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.201.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.201.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.202.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.202.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.202.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.203.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.203.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.203.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.204.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.204.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.204.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.205.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.205.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.205.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.206.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.206.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.206.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.207.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.207.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.207.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.208.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.208.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.208.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.209.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.209.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.209.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.21.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.21.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.21.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.210.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.210.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.210.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.211.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.211.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.211.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.212.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.212.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.212.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.213.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.213.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.213.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.214.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.214.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.214.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.215.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.215.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.215.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.216.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.216.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.216.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.217.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.217.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.217.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.218.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.218.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.218.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.219.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.219.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.219.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.22.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.22.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.22.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.220.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.220.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.220.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.221.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.221.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.221.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.222.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.222.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.222.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.223.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.223.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.223.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.224.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.224.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.224.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.225.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.225.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.225.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.226.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.226.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.226.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.227.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.227.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.227.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.228.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.228.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.228.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.229.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.229.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.229.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.23.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.23.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.23.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.230.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.230.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.230.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.231.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.231.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.231.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.232.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.232.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.232.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.233.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.233.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.233.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.234.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.234.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.234.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.235.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.235.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.235.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.236.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.236.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.236.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.237.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.237.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.237.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.238.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.238.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.238.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.239.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.239.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.239.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.24.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.24.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.24.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.240.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.240.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.240.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.241.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.241.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.241.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.242.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.242.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.242.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.243.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.243.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.243.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.244.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.244.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.244.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.245.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.245.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.245.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.246.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.246.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.246.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.247.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.247.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.247.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.248.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.248.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.248.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.249.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.249.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.249.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.25.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.25.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.25.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.250.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.250.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.250.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.251.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.251.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.251.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.252.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.252.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.252.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.253.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.253.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.253.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.254.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.254.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.254.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.255.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.255.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.255.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.26.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.26.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.26.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.27.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.27.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.27.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.28.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.28.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.28.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.29.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.29.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.29.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.3.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.3.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.3.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.30.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.30.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.30.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.31.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.31.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.31.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.32.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.32.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.32.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.33.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.33.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.33.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.34.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.34.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.34.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.35.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.35.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.35.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.36.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.36.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.36.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.37.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.37.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.37.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.38.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.38.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.38.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.39.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.39.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.39.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.4.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.4.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.4.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.40.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.40.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.40.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.41.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.41.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.41.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.42.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.42.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.42.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.43.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.43.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.43.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.44.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.44.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.44.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.45.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.45.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.45.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.46.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.46.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.46.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.47.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.47.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.47.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.48.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.48.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.48.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.49.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.49.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.49.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.5.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.5.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.5.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.50.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.50.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.50.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.51.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.51.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.51.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.52.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.52.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.52.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.53.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.53.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.53.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.54.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.54.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.54.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.55.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.55.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.55.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.56.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.56.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.56.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.57.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.57.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.57.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.58.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.58.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.58.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.59.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.59.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.59.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.6.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.6.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.6.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.60.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.60.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.60.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.61.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.61.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.61.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.62.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.62.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.62.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.63.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.63.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.63.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.64.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.64.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.64.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.65.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.65.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.65.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.66.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.66.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.66.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.67.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.67.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.67.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.68.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.68.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.68.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.69.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.69.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.69.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.7.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.7.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.7.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.70.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.70.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.70.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.71.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.71.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.71.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.72.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.72.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.72.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.73.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.73.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.73.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.74.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.74.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.74.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.75.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.75.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.75.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.76.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.76.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.76.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.77.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.77.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.77.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.78.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.78.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.78.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.79.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.79.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.79.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.8.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.8.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.8.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.80.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.80.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.80.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.81.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.81.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.81.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.82.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.82.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.82.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.83.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.83.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.83.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.84.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.84.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.84.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.85.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.85.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.85.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.86.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.86.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.86.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.87.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.87.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.87.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.88.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.88.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.88.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.89.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.89.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.89.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.9.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.9.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.9.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.90.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.90.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.90.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.91.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.91.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.91.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.92.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.92.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.92.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.93.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.93.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.93.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.94.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.94.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.94.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.95.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.95.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.95.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.96.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.96.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.96.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.97.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.97.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.97.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.98.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.98.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.98.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.99.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.99.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.experts.99.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.gate.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.0.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.0.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.0.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.1.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.1.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.1.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.10.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.10.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.10.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.100.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.100.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.100.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.101.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.101.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.101.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.102.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.102.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.102.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.103.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.103.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.103.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.104.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.104.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.104.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.105.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.105.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.105.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.106.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.106.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.106.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.107.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.107.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.107.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.108.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.108.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.108.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.109.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.109.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.109.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.11.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.11.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.11.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.110.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.110.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.110.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.111.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.111.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.111.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.112.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.112.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.112.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.113.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.113.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.113.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.114.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.114.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.114.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.115.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.115.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.115.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.116.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.116.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.116.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.117.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.117.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.117.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.118.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.118.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.118.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.119.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.119.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.119.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.12.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.12.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.12.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.120.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.120.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.120.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.121.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.121.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.121.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.122.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.122.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.122.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.123.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.123.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.123.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.124.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.124.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.124.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.125.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.125.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.125.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.126.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.126.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.126.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.127.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.127.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.127.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.128.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.128.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.128.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.129.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.129.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.129.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.13.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.13.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.13.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.130.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.130.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.130.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.131.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.131.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.131.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.132.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.132.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.132.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.133.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.133.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.133.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.134.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.134.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.134.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.135.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.135.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.135.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.136.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.136.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.136.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.137.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.137.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.137.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.138.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.138.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.138.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.139.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.139.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.139.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.14.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.14.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.14.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.140.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.140.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.140.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.141.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.141.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.141.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.142.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.142.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.142.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.143.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.143.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.143.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.144.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.144.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.144.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.145.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.145.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.145.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.146.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.146.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.146.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.147.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.147.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.147.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.148.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.148.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.148.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.149.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.149.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.149.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.15.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.15.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.15.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.150.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.150.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.150.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.151.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.151.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.151.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.152.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.152.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.152.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.153.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.153.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.153.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.154.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.154.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.154.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.155.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.155.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.155.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.156.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.156.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.156.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.157.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.157.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.157.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.158.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.158.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.158.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.159.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.159.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.159.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.16.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.16.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.16.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.160.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.160.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.160.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.161.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.161.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.161.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.162.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.162.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.162.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.163.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.163.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.163.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.164.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.164.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.164.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.165.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.165.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.165.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.166.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.166.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.166.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.167.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.167.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.167.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.168.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.168.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.168.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.169.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.169.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.169.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.17.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.17.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.17.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.170.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.170.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.170.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.171.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.171.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.171.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.172.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.172.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.172.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.173.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.173.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.173.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.174.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.174.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.174.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.175.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.175.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.175.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.176.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.176.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.176.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.177.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.177.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.177.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.178.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.178.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.178.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.179.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.179.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.179.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.18.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.18.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.18.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.180.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.180.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.180.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.181.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.181.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.181.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.182.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.182.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.182.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.183.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.183.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.183.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.184.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.184.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.184.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.185.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.185.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.185.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.186.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.186.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.186.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.187.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.187.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.187.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.188.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.188.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.188.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.189.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.189.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.189.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.19.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.19.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.19.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.190.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.190.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.190.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.191.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.191.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.191.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.192.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.192.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.192.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.193.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.193.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.193.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.194.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.194.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.194.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.195.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.195.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.195.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.196.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.196.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.196.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.197.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.197.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.197.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.198.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.198.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.198.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.199.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.199.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.199.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.2.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.2.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.2.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.20.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.20.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.20.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.200.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.200.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.200.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.201.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.201.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.201.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.202.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.202.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.202.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.203.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.203.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.203.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.204.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.204.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.204.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.205.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.205.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.205.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.206.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.206.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.206.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.207.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.207.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.207.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.208.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.208.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.208.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.209.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.209.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.209.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.21.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.21.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.21.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.210.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.210.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.210.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.211.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.211.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.211.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.212.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.212.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.212.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.213.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.213.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.213.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.214.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.214.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.214.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.215.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.215.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.215.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.216.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.216.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.216.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.217.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.217.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.217.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.218.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.218.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.218.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.219.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.219.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.219.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.22.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.22.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.22.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.220.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.220.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.220.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.221.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.221.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.221.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.222.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.222.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.222.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.223.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.223.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.223.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.224.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.224.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.224.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.225.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.225.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.225.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.226.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.226.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.226.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.227.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.227.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.227.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.228.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.228.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.228.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.229.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.229.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.229.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.23.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.23.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.23.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.230.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.230.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.230.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.231.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.231.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.231.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.232.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.232.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.232.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.233.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.233.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.233.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.234.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.234.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.234.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.235.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.235.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.235.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.236.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.236.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.236.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.237.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.237.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.237.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.238.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.238.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.238.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.239.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.239.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.239.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.24.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.24.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.24.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.240.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.240.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.240.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.241.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.241.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.241.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.242.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.242.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.242.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.243.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.243.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.243.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.244.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.244.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.244.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.245.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.245.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.245.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.246.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.246.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.246.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.247.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.247.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.247.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.248.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.248.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.248.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.249.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.249.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.249.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.25.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.25.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.25.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.250.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.250.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.250.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.251.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.251.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.251.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.252.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.252.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.252.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.253.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.253.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.253.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.254.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.254.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.254.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.255.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.255.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.255.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.26.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.26.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.26.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.27.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.27.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.27.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.28.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.28.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.28.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.29.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.29.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.29.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.3.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.3.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.3.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.30.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.30.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.30.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.31.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.31.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.31.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.32.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.32.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.32.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.33.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.33.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.33.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.34.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.34.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.34.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.35.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.35.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.35.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.36.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.36.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.36.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.37.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.37.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.37.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.38.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.38.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.38.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.39.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.39.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.39.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.4.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.4.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.4.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.40.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.40.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.40.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.41.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.41.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.41.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.42.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.42.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.42.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.43.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.43.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.43.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.44.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.44.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.44.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.45.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.45.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.45.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.46.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.46.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.46.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.47.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.47.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.47.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.48.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.48.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.48.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.49.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.49.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.49.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.5.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.5.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.5.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.50.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.50.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.50.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.51.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.51.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.51.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.52.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.52.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.52.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.53.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.53.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.53.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.54.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.54.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.54.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.55.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.55.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.55.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.56.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.56.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.56.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.57.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.57.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.57.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.58.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.58.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.58.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.59.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.59.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.59.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.6.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.6.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.6.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.60.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.60.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.60.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.61.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.61.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.61.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.62.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.62.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.62.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.63.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.63.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.63.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.64.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.64.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.64.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.65.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.65.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.65.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.66.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.66.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.66.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.67.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.67.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.67.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.68.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.68.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.68.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.69.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.69.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.69.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.7.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.7.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.7.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.70.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.70.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.70.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.71.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.71.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.71.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.72.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.72.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.72.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.73.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.73.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.73.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.74.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.74.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.74.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.75.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.75.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.75.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.76.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.76.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.76.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.77.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.77.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.77.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.78.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.78.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.78.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.79.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.79.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.79.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.8.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.8.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.8.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.80.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.80.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.80.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.81.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.81.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.81.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.82.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.82.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.82.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.83.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.83.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.83.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.84.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.84.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.84.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.85.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.85.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.85.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.86.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.86.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.86.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.87.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.87.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.87.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.88.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.88.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.88.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.89.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.89.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.89.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.9.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.9.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.9.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.90.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.90.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.90.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.91.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.91.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.91.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.92.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.92.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.92.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.93.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.93.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.93.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.94.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.94.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.94.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.95.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.95.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.95.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.96.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.96.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.96.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.97.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.97.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.97.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.98.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.98.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.98.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.99.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.99.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.experts.99.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.mlp.gate.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00025-of-00033.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.A_log": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.dt_bias": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.norm.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.0.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.0.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.0.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.1.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.1.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.1.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.10.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.10.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.10.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.100.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.100.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.100.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.101.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.101.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.101.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.102.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.102.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.102.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.103.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.103.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.103.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.104.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.104.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.104.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.105.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.105.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.105.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.106.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.106.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.106.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.107.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.107.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.107.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.108.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.108.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.108.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.109.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.109.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.109.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.11.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.11.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.11.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.110.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.110.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.110.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.111.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.111.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.111.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.112.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.112.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.112.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.113.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.113.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.113.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.114.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.114.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.114.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.115.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.115.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.115.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.116.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.116.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.116.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.117.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.117.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.117.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.118.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.118.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.118.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.119.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.119.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.119.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.12.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.12.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.12.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.120.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.120.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.120.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.121.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.121.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.121.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.122.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.122.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.122.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.123.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.123.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.123.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.124.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.124.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.124.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.125.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.125.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.125.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.126.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.126.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.126.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.127.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.127.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.127.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.128.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.128.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.128.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.129.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.129.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.129.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.13.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.13.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.13.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.130.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.130.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.130.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.131.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.131.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.131.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.132.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.132.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.132.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.133.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.133.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.133.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.134.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.134.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.134.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.135.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.135.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.135.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.136.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.136.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.136.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.137.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.137.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.137.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.138.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.138.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.138.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.139.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.139.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.139.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.14.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.14.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.14.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.140.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.140.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.140.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.141.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.141.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.141.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.142.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.142.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.142.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.143.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.143.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.143.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.144.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.144.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.144.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.145.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.145.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.145.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.146.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.146.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.146.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.147.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.147.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.147.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.148.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.148.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.148.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.149.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.149.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.149.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.15.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.15.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.15.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.150.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.150.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.150.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.151.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.151.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.151.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.152.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.152.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.152.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.153.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.153.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.153.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.154.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.154.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.154.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.155.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.155.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.155.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.156.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.156.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.156.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.157.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.157.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.157.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.158.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.158.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.158.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.159.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.159.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.159.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.16.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.16.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.16.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.160.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.160.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.160.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.161.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.161.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.161.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.162.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.162.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.162.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.163.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.163.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.163.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.164.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.164.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.164.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.165.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.165.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.165.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.166.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.166.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.166.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.167.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.167.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.167.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.168.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.168.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.168.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.169.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.169.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.169.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.17.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.17.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.17.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.170.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.170.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.170.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.171.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.171.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.171.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.172.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.172.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.172.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.173.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.173.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.173.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.174.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.174.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.174.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.175.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.175.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.175.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.176.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.176.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.176.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.177.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.177.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.177.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.178.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.178.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.178.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.179.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.179.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.179.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.18.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.18.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.18.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.180.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.180.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.180.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.181.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.181.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.181.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.182.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.182.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.182.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.183.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.183.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.183.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.184.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.184.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.184.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.185.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.185.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.185.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.186.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.186.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.186.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.187.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.187.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.187.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.188.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.188.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.188.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.189.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.189.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.189.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.19.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.19.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.19.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.190.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.190.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.190.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.191.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.191.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.191.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.192.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.192.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.192.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.193.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.193.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.193.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.194.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.194.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.194.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.195.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.195.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.195.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.196.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.196.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.196.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.197.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.197.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.197.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.198.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.198.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.198.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.199.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.199.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.199.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.2.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.2.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.2.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.20.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.20.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.20.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.200.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.200.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.200.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.201.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.201.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.201.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.202.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.202.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.202.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.203.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.203.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.203.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.204.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.204.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.204.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.205.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.205.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.205.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.206.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.206.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.206.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.207.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.207.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.207.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.208.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.208.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.208.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.209.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.209.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.209.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.21.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.21.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.21.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.210.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.210.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.210.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.211.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.211.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.211.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.212.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.212.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.212.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.213.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.213.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.213.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.214.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.214.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.214.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.215.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.215.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.215.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.216.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.216.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.216.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.217.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.217.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.217.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.218.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.218.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.218.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.219.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.219.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.219.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.22.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.22.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.22.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.220.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.220.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.220.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.221.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.221.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.221.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.222.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.222.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.222.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.223.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.223.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.223.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.224.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.224.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.224.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.225.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.225.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.225.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.226.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.226.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.226.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.227.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.227.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.227.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.228.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.228.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.228.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.229.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.229.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.229.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.23.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.23.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.23.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.230.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.230.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.230.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.231.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.231.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.231.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.232.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.232.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.232.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.233.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.233.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.233.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.234.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.234.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.234.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.235.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.235.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.235.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.236.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.236.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.236.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.237.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.237.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.237.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.238.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.238.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.238.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.239.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.239.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.239.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.24.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.24.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.24.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.240.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.240.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.240.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.241.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.241.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.241.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.242.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.242.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.242.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.243.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.243.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.243.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.244.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.244.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.244.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.245.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.245.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.245.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.246.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.246.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.246.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.247.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.247.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.247.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.248.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.248.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.248.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.249.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.249.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.249.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.25.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.25.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.25.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.250.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.250.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.250.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.251.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.251.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.251.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.252.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.252.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.252.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.253.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.253.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.253.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.254.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.254.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.254.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.255.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.255.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.255.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.26.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.26.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.26.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.27.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.27.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.27.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.28.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.28.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.28.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.29.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.29.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.29.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.3.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.3.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.3.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.30.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.30.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.30.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.31.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.31.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.31.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.32.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.32.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.32.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.33.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.33.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.33.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.34.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.34.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.34.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.35.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.35.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.35.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.36.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.36.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.36.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.37.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.37.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.37.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.38.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.38.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.38.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.39.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.39.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.39.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.4.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.4.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.4.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.40.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.40.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.40.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.41.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.41.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.41.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.42.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.42.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.42.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.43.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.43.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.43.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.44.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.44.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.44.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.45.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.45.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.45.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.46.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.46.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.46.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.47.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.47.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.47.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.48.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.48.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.48.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.49.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.49.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.49.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.5.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.5.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.5.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.50.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.50.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.50.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.51.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.51.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.51.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.52.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.52.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.52.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.53.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.53.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.53.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.54.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.54.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.54.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.55.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.55.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.55.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.56.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.56.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.56.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.57.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.57.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.57.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.58.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.58.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.58.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.59.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.59.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.59.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.6.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.6.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.6.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.60.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.60.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.60.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.61.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.61.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.61.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.62.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.62.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.62.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.63.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.63.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.63.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.64.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.64.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.64.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.65.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.65.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.65.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.66.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.66.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.66.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.67.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.67.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.67.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.68.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.68.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.68.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.69.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.69.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.69.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.7.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.7.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.7.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.70.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.70.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.70.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.71.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.71.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.71.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.72.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.72.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.72.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.73.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.73.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.73.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.74.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.74.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.74.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.75.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.75.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.75.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.76.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.76.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.76.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.77.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.77.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.77.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.78.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.78.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.78.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.79.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.79.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.79.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.8.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.8.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.8.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.80.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.80.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.80.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.81.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.81.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.81.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.82.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.82.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.82.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.83.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.83.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.83.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.84.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.84.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.84.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.85.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.85.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.85.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.86.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.86.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.86.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.87.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.87.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.87.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.88.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.88.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.88.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.89.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.89.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.89.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.9.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.9.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.9.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.90.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.90.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.90.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.91.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.91.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.91.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.92.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.92.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.92.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.93.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.93.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.93.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.94.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.94.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.94.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.95.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.95.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.95.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.96.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.96.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.96.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.97.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.97.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.97.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.98.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.98.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.98.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.99.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.99.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.experts.99.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.gate.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.A_log": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.dt_bias": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.norm.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.0.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.0.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.0.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.1.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.1.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.1.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.10.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.10.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.10.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.100.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.100.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.100.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.101.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.101.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.101.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.102.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.102.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.102.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.103.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.103.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.103.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.104.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.104.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.104.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.105.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.105.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.105.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.106.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.106.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.106.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.107.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.107.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.107.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.108.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.108.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.108.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.109.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.109.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.109.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.11.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.11.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.11.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.110.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.110.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.110.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.111.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.111.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.111.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.112.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.112.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.112.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.113.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.113.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.113.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.114.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.114.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.114.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.115.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.115.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.115.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.116.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.116.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.116.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.117.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.117.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.117.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.118.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.118.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.118.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.119.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.119.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.119.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.12.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.12.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.12.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.120.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.120.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.120.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.121.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.121.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.121.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.122.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.122.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.122.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.123.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.123.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.123.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.124.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.124.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.124.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.125.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.125.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.125.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.126.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.126.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.126.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.127.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.127.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.127.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.128.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.128.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.128.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.129.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.129.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.129.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.13.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.13.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.13.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.130.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.130.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.130.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.131.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.131.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.131.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.132.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.132.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.132.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.133.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.133.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.133.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.134.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.134.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.134.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.135.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.135.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.135.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.136.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.136.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.136.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.137.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.137.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.137.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.138.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.138.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.138.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.139.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.139.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.139.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.14.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.14.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.14.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.140.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.140.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.140.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.141.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.141.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.141.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.142.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.142.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.142.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.143.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.143.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.143.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.144.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.144.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.144.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.145.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.145.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.145.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.146.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.146.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.146.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.147.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.147.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.147.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.148.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.148.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.148.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.149.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.149.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.149.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.15.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.15.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.15.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.150.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.150.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.150.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.151.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.151.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.151.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.152.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.152.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.152.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.153.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.153.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.153.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.154.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.154.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.154.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.155.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.155.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.155.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.156.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.156.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.156.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.157.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.157.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.157.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.158.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.158.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.158.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.159.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.159.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.159.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.16.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.16.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.16.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.160.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.160.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.160.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.161.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.161.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.161.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.162.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.162.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.162.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.163.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.163.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.163.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.164.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.164.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.164.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.165.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.165.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.165.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.166.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.166.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.166.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.167.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.167.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.167.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.168.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.168.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.168.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.169.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.169.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.169.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.17.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.17.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.17.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.170.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.170.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.170.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.171.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.171.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.171.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.172.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.172.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.172.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.173.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.173.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.173.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.174.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.174.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.174.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.175.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.175.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.175.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.176.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.176.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.176.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.177.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.177.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.177.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.178.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.178.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.178.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.179.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.179.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.179.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.18.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.18.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.18.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.180.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.180.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.180.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.181.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.181.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.181.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.182.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.182.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.182.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.183.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.183.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.183.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.184.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.184.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.184.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.185.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.185.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.185.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.186.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.186.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.186.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.187.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.187.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.187.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.188.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.188.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.188.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.189.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.189.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.189.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.19.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.19.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.19.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.190.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.190.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.190.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.191.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.191.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.191.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.192.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.192.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.192.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.193.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.193.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.193.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.194.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.194.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.194.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.195.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.195.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.195.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.196.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.196.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.196.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.197.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.197.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.197.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.198.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.198.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.198.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.199.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.199.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.199.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.2.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.2.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.2.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.20.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.20.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.20.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.200.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.200.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.200.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.201.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.201.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.201.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.202.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.202.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.202.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.203.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.203.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.203.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.204.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.204.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.204.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.205.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.205.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.205.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.206.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.206.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.206.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.207.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.207.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.207.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.208.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.208.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.208.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.209.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.209.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.209.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.21.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.21.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.21.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.210.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.210.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.210.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.211.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.211.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.211.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.212.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.212.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.212.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.213.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.213.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.213.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.214.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.214.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.214.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.215.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.215.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.215.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.216.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.216.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.216.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.217.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.217.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.217.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.218.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.218.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.218.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.219.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.219.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.219.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.22.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.22.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.22.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.220.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.220.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.220.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.221.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.221.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.221.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.222.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.222.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.222.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.223.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.223.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.223.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.224.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.224.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.224.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.225.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.225.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.225.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.226.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.226.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.226.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.227.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.227.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.227.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.228.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.228.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.228.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.229.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.229.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.229.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.23.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.23.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.23.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.230.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.230.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.230.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.231.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.231.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.231.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.232.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.232.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.232.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.233.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.233.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.233.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.234.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.234.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.234.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.235.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.235.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.235.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.236.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.236.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.236.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.237.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.237.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.237.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.238.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.238.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.238.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.239.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.239.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.239.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.24.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.24.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.24.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.240.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.240.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.240.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.241.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.241.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.241.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.242.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.242.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.242.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.243.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.243.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.243.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.244.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.244.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.244.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.245.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.245.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.245.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.246.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.246.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.246.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.247.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.247.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.247.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.248.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.248.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.248.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.249.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.249.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.249.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.25.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.25.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.25.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.250.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.250.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.250.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.251.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.251.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.251.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.252.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.252.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.252.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.253.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.253.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.253.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.254.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.254.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.254.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.255.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.255.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.255.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.26.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.26.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.26.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.27.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.27.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.27.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.28.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.28.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.28.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.29.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.29.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.29.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.3.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.3.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.3.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.30.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.30.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.30.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.31.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.31.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.31.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.32.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.32.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.32.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.33.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.33.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.33.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.34.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.34.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.34.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.35.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.35.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.35.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.36.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.36.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.36.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.37.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.37.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.37.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.38.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.38.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.38.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.39.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.39.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.39.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.4.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.4.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.4.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.40.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.40.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.40.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.41.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.41.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.41.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.42.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.42.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.42.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.43.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.43.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.43.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.44.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.44.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.44.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.45.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.45.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.45.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.46.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.46.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.46.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.47.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.47.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.47.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.48.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.48.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.48.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.49.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.49.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.49.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.5.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.5.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.5.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.50.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.50.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.50.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.51.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.51.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.51.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.52.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.52.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.52.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.53.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.53.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.53.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.54.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.54.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.54.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.55.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.55.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.55.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.56.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.56.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.56.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.57.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.57.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.57.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.58.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.58.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.58.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.59.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.59.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.59.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.6.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.6.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.6.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.60.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.60.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.60.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.61.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.61.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.61.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.62.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.62.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.62.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.63.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.63.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.63.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.64.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.64.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.64.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.65.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.65.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.65.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.66.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.66.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.66.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.67.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.67.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.67.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.68.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.68.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.68.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.69.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.69.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.69.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.7.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.7.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.7.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.70.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.70.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.70.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.71.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.71.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.71.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.72.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.72.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.72.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.73.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.73.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.73.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.74.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.74.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.74.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.75.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.75.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.75.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.76.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.76.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.76.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.77.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.77.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.77.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.78.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.78.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.78.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.79.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.79.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.79.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.8.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.8.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.8.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.80.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.80.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.80.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.81.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.81.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.81.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.82.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.82.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.82.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.83.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.83.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.83.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.84.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.84.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.84.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.85.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.85.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.85.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.86.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.86.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.86.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.87.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.87.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.87.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.88.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.88.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.88.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.89.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.89.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.89.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.9.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.9.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.9.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.90.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.90.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.90.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.91.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.91.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.91.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.92.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.92.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.92.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.93.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.93.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.93.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.94.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.94.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.94.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.95.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.95.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.95.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.96.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.96.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.96.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.97.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.97.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.97.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.98.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.98.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.98.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.99.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.99.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.experts.99.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.gate.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00027-of-00033.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.A_log": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.dt_bias": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.norm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.0.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.0.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.0.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.1.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.1.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.1.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.10.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.10.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.10.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.100.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.100.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.100.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.101.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.101.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.101.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.102.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.102.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.102.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.103.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.103.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.103.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.104.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.104.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.104.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.105.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.105.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.105.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.106.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.106.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.106.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.107.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.107.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.107.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.108.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.108.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.108.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.109.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.109.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.109.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.11.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.11.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.11.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.110.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.110.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.110.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.111.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.111.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.111.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.112.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.112.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.112.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.113.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.113.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.113.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.114.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.114.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.114.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.115.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.115.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.115.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.116.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.116.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.116.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.117.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.117.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.117.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.118.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.118.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.118.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.119.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.119.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.119.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.12.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.12.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.12.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.120.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.120.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.120.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.121.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.121.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.121.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.122.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.122.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.122.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.123.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.123.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.123.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.124.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.124.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.124.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.125.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.125.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.125.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.126.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.126.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.126.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.127.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.127.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.127.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.128.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.128.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.128.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.129.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.129.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.129.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.13.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.13.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.13.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.130.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.130.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.130.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.131.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.131.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.131.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.132.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.132.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.132.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.133.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.133.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.133.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.134.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.134.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.134.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.135.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.135.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.135.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.136.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.136.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.136.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.137.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.137.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.137.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.138.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.138.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.138.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.139.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.139.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.139.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.14.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.14.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.14.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.140.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.140.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.140.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.141.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.141.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.141.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.142.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.142.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.142.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.143.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.143.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.143.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.144.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.144.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.144.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.145.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.145.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.145.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.146.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.146.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.146.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.147.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.147.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.147.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.148.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.148.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.148.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.149.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.149.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.149.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.15.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.15.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.15.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.150.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.150.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.150.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.151.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.151.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.151.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.152.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.152.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.152.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.153.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.153.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.153.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.154.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.154.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.154.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.155.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.155.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.155.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.156.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.156.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.156.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.157.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.157.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.157.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.158.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.158.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.158.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.159.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.159.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.159.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.16.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.16.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.16.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.160.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.160.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.160.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.161.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.161.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.161.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.162.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.162.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.162.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.163.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.163.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.163.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.164.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.164.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.164.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.165.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.165.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.165.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.166.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.166.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.166.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.167.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.167.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.167.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.168.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.168.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.168.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.169.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.169.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.169.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.17.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.17.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.17.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.170.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.170.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.170.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.171.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.171.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.171.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.172.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.172.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.172.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.173.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.173.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.173.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.174.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.174.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.174.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.175.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.175.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.175.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.176.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.176.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.176.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.177.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.177.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.177.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.178.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.178.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.178.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.179.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.179.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.179.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.18.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.18.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.18.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.180.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.180.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.180.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.181.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.181.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.181.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.182.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.182.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.182.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.183.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.183.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.183.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.184.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.184.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.184.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.185.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.185.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.185.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.186.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.186.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.186.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.187.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.187.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.187.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.188.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.188.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.188.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.189.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.189.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.189.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.19.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.19.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.19.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.190.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.190.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.190.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.191.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.191.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.191.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.192.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.192.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.192.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.193.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.193.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.193.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.194.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.194.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.194.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.195.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.195.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.195.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.196.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.196.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.196.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.197.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.197.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.197.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.198.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.198.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.198.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.199.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.199.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.199.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.2.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.2.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.2.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.20.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.20.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.20.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.200.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.200.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.200.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.201.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.201.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.201.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.202.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.202.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.202.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.203.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.203.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.203.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.204.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.204.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.204.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.205.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.205.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.205.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.206.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.206.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.206.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.207.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.207.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.207.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.208.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.208.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.208.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.209.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.209.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.209.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.21.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.21.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.21.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.210.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.210.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.210.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.211.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.211.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.211.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.212.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.212.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.212.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.213.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.213.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.213.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.214.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.214.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.214.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.215.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.215.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.215.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.216.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.216.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.216.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.217.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.217.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.217.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.218.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.218.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.218.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.219.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.219.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.219.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.22.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.22.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.22.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.220.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.220.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.220.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.221.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.221.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.221.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.222.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.222.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.222.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.223.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.223.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.223.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.224.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.224.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.224.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.225.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.225.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.225.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.226.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.226.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.226.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.227.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.227.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.227.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.228.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.228.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.228.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.229.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.229.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.229.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.23.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.23.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.23.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.230.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.230.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.230.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.231.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.231.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.231.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.232.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.232.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.232.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.233.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.233.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.233.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.234.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.234.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.234.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.235.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.235.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.235.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.236.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.236.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.236.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.237.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.237.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.237.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.238.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.238.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.238.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.239.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.239.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.239.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.24.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.24.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.24.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.240.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.240.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.240.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.241.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.241.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.241.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.242.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.242.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.242.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.243.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.243.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.243.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.244.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.244.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.244.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.245.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.245.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.245.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.246.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.246.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.246.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.247.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.247.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.247.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.248.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.248.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.248.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.249.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.249.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.249.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.25.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.25.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.25.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.250.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.250.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.250.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.251.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.251.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.251.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.252.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.252.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.252.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.253.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.253.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.253.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.254.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.254.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.254.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.255.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.255.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.255.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.26.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.26.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.26.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.27.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.27.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.27.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.28.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.28.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.28.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.29.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.29.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.29.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.3.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.3.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.3.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.30.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.30.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.30.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.31.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.31.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.31.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.32.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.32.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.32.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.33.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.33.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.33.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.34.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.34.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.34.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.35.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.35.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.35.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.36.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.36.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.36.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.37.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.37.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.37.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.38.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.38.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.38.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.39.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.39.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.39.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.4.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.4.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.4.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.40.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.40.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.40.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.41.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.41.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.41.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.42.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.42.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.42.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.43.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.43.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.43.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.44.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.44.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.44.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.45.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.45.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.45.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.46.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.46.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.46.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.47.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.47.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.47.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.48.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.48.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.48.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.49.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.49.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.49.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.5.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.5.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.5.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.50.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.50.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.50.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.51.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.51.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.51.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.52.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.52.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.52.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.53.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.53.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.53.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.54.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.54.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.54.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.55.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.55.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.55.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.56.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.56.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.56.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.57.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.57.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.57.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.58.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.58.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.58.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.59.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.59.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.59.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.6.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.6.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.6.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.60.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.60.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.60.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.61.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.61.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.61.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.62.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.62.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.62.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.63.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.63.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.63.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.64.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.64.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.64.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.65.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.65.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.65.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.66.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.66.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.66.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.67.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.67.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.67.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.68.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.68.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.68.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.69.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.69.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.69.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.7.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.7.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.7.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.70.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.70.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.70.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.71.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.71.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.71.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.72.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.72.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.72.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.73.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.73.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.73.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.74.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.74.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.74.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.75.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.75.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.75.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.76.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.76.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.76.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.77.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.77.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.77.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.78.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.78.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.78.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.79.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.79.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.79.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.8.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.8.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.8.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.80.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.80.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.80.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.81.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.81.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.81.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.82.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.82.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.82.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.83.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.83.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.83.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.84.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.84.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.84.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.85.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.85.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.85.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.86.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.86.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.86.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.87.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.87.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.87.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.88.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.88.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.88.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.89.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.89.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.89.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.9.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.9.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.9.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.90.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.90.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.90.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.91.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.91.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.91.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.92.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.92.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.92.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.93.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.93.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.93.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.94.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.94.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.94.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.95.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.95.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.95.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.96.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.96.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.96.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.97.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.97.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.97.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.98.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.98.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.98.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.99.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.99.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.experts.99.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.gate.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.0.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.0.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.0.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.1.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.1.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.1.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.10.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.10.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.10.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.100.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.100.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.100.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.101.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.101.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.101.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.102.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.102.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.102.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.103.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.103.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.103.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.104.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.104.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.104.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.105.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.105.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.105.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.106.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.106.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.106.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.107.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.107.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.107.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.108.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.108.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.108.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.109.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.109.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.109.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.11.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.11.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.11.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.110.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.110.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.110.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.111.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.111.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.111.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.112.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.112.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.112.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.113.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.113.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.113.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.114.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.114.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.114.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.115.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.115.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.115.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.116.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.116.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.116.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.117.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.117.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.117.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.118.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.118.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.118.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.119.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.119.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.119.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.12.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.12.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.12.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.120.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.120.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.120.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.121.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.121.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.121.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.122.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.122.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.122.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.123.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.123.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.123.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.124.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.124.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.124.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.125.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.125.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.125.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.126.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.126.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.126.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.127.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.127.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.127.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.128.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.128.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.128.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.129.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.129.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.129.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.13.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.13.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.13.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.130.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.130.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.130.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.131.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.131.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.131.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.132.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.132.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.132.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.133.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.133.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.133.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.134.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.134.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.134.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.135.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.135.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.135.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.136.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.136.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.136.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.137.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.137.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.137.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.138.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.138.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.138.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.139.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.139.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.139.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.14.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.14.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.14.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.140.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.140.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.140.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.141.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.141.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.141.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.142.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.142.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.142.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.143.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.143.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.143.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.144.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.144.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.144.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.145.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.145.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.145.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.146.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.146.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.146.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.147.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.147.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.147.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.148.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.148.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.148.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.149.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.149.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.149.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.15.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.15.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.15.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.150.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.150.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.150.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.151.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.151.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.151.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.152.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.152.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.152.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.153.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.153.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.153.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.154.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.154.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.154.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.155.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.155.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.155.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.156.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.156.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.156.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.157.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.157.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.157.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.158.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.158.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.158.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.159.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.159.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.159.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.16.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.16.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.16.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.160.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.160.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.160.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.161.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.161.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.161.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.162.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.162.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.162.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.163.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.163.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.163.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.164.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.164.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.164.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.165.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.165.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.165.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.166.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.166.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.166.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.167.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.167.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.167.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.168.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.168.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.168.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.169.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.169.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.169.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.17.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.17.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.17.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.170.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.170.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.170.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.171.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.171.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.171.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.172.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.172.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.172.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.173.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.173.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.173.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.174.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.174.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.174.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.175.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.175.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.175.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.176.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.176.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.176.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.177.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.177.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.177.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.178.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.178.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.178.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.179.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.179.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.179.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.18.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.18.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.18.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.180.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.180.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.180.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.181.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.181.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.181.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.182.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.182.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.182.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.183.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.183.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.183.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.184.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.184.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.184.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.185.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.185.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.185.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.186.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.186.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.186.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.187.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.187.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.187.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.188.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.188.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.188.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.189.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.189.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.189.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.19.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.19.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.19.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.190.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.190.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.190.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.191.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.191.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.191.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.192.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.192.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.192.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.193.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.193.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.193.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.194.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.194.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.194.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.195.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.195.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.195.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.196.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.196.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.196.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.197.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.197.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.197.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.198.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.198.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.198.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.199.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.199.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.199.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.2.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.2.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.2.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.20.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.20.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.20.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.200.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.200.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.200.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.201.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.201.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.201.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.202.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.202.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.202.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.203.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.203.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.203.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.204.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.204.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.204.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.205.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.205.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.205.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.206.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.206.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.206.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.207.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.207.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.207.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.208.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.208.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.208.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.209.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.209.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.209.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.21.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.21.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.21.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.210.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.210.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.210.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.211.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.211.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.211.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.212.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.212.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.212.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.213.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.213.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.213.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.214.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.214.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.214.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.215.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.215.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.215.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.216.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.216.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.216.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.217.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.217.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.217.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.218.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.218.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.218.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.219.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.219.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.219.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.22.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.22.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.22.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.220.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.220.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.220.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.221.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.221.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.221.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.222.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.222.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.222.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.223.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.223.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.223.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.224.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.224.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.224.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.225.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.225.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.225.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.226.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.226.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.226.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.227.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.227.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.227.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.228.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.228.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.228.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.229.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.229.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.229.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.23.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.23.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.23.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.230.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.230.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.230.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.231.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.231.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.231.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.232.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.232.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.232.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.233.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.233.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.233.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.234.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.234.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.234.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.235.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.235.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.235.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.236.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.236.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.236.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.237.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.237.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.237.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.238.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.238.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.238.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.239.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.239.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.239.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.24.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.24.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.24.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.240.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.240.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.240.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.241.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.241.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.241.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.242.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.242.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.242.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.243.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.243.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.243.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.244.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.244.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.244.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.245.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.245.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.245.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.246.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.246.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.246.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.247.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.247.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.247.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.248.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.248.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.248.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.249.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.249.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.249.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.25.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.25.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.25.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.250.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.250.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.250.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.251.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.251.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.251.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.252.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.252.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.252.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.253.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.253.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.253.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.254.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.254.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.254.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.255.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.255.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.255.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.26.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.26.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.26.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.27.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.27.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.27.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.28.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.28.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.28.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.29.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.29.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.29.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.3.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.3.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.3.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.30.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.30.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.30.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.31.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.31.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.31.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.32.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.32.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.32.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.33.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.33.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.33.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.34.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.34.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.34.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.35.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.35.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.35.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.36.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.36.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.36.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.37.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.37.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.37.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.38.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.38.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.38.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.39.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.39.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.39.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.4.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.4.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.4.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.40.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.40.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.40.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.41.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.41.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.41.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.42.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.42.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.42.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.43.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.43.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.43.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.44.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.44.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.44.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.45.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.45.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.45.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.46.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.46.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.46.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.47.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.47.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.47.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.48.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.48.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.48.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.49.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.49.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.49.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.5.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.5.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.5.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.50.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.50.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.50.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.51.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.51.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.51.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.52.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.52.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.52.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.53.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.53.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.53.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.54.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.54.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.54.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.55.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.55.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.55.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.56.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.56.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.56.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.57.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.57.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.57.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.58.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.58.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.58.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.59.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.59.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.59.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.6.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.6.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.6.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.60.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.60.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.60.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.61.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.61.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.61.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.62.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.62.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.62.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.63.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.63.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.63.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.64.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.64.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.64.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.65.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.65.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.65.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.66.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.66.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.66.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.67.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.67.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.67.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.68.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.68.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.68.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.69.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.69.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.69.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.7.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.7.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.7.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.70.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.70.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.70.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.71.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.71.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.71.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.72.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.72.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.72.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.73.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.73.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.73.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.74.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.74.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.74.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.75.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.75.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.75.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.76.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.76.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.76.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.77.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.77.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.77.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.78.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.78.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.78.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.79.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.79.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.79.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.8.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.8.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.8.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.80.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.80.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.80.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.81.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.81.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.81.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.82.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.82.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.82.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.83.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.83.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.83.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.84.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.84.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.84.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.85.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.85.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.85.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.86.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.86.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.86.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.87.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.87.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.87.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.88.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.88.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.88.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.89.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.89.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.89.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.9.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.9.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.9.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.90.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.90.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.90.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.91.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.91.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.91.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.92.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.92.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.92.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.93.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.93.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.93.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.94.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.94.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.94.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.95.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.95.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.95.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.96.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.96.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.96.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.97.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.97.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.97.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.98.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.98.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.98.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.99.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.99.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.experts.99.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.35.mlp.gate.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", + "model.language_model.layers.36.input_layernorm.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.A_log": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.dt_bias": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.norm.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.0.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.0.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.0.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.1.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.1.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.1.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.10.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.10.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.10.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.100.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.100.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.100.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.101.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.101.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.101.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.102.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.102.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.102.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.103.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.103.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.103.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.104.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.104.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.104.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.105.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.105.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.105.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.106.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.106.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.106.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.107.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.107.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.107.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.108.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.108.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.108.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.109.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.109.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.109.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.11.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.11.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.11.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.110.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.110.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.110.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.111.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.111.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.111.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.112.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.112.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.112.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.113.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.113.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.113.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.114.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.114.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.114.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.115.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.115.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.115.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.116.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.116.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.116.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.117.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.117.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.117.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.118.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.118.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.118.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.119.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.119.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.119.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.12.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.12.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.12.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.120.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.120.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.120.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.121.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.121.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.121.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.122.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.122.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.122.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.123.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.123.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.123.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.124.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.124.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.124.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.125.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.125.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.125.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.126.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.126.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.126.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.127.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.127.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.127.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.128.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.128.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.128.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.129.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.129.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.129.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.13.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.13.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.13.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.130.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.130.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.130.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.131.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.131.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.131.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.132.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.132.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.132.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.133.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.133.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.133.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.134.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.134.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.134.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.135.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.135.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.135.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.136.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.136.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.136.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.137.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.137.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.137.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.138.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.138.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.138.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.139.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.139.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.139.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.14.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.14.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.14.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.140.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.140.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.140.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.141.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.141.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.141.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.142.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.142.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.142.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.143.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.143.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.143.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.144.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.144.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.144.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.145.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.145.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.145.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.146.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.146.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.146.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.147.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.147.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.147.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.148.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.148.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.148.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.149.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.149.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.149.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.15.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.15.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.15.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.150.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.150.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.150.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.151.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.151.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.151.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.152.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.152.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.152.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.153.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.153.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.153.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.154.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.154.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.154.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.155.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.155.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.155.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.156.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.156.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.156.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.157.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.157.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.157.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.158.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.158.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.158.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.159.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.159.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.159.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.16.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.16.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.16.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.160.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.160.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.160.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.161.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.161.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.161.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.162.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.162.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.162.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.163.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.163.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.163.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.164.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.164.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.164.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.165.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.165.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.165.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.166.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.166.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.166.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.167.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.167.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.167.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.168.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.168.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.168.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.169.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.169.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.169.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.17.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.17.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.17.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.170.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.170.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.170.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.171.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.171.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.171.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.172.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.172.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.172.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.173.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.173.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.173.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.174.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.174.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.174.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.175.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.175.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.175.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.176.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.176.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.176.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.177.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.177.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.177.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.178.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.178.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.178.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.179.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.179.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.179.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.18.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.18.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.18.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.180.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.180.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.180.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.181.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.181.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.181.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.182.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.182.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.182.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.183.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.183.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.183.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.184.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.184.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.184.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.185.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.185.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.185.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.186.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.186.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.186.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.187.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.187.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.187.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.188.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.188.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.188.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.189.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.189.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.189.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.19.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.19.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.19.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.190.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.190.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.190.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.191.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.191.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.191.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.192.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.192.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.192.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.193.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.193.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.193.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.194.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.194.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.194.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.195.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.195.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.195.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.196.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.196.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.196.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.197.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.197.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.197.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.198.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.198.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.198.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.199.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.199.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.199.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.2.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.2.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.2.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.20.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.20.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.20.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.200.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.200.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.200.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.201.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.201.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.201.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.202.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.202.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.202.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.203.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.203.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.203.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.204.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.204.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.204.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.205.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.205.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.205.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.206.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.206.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.206.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.207.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.207.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.207.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.208.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.208.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.208.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.209.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.209.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.209.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.21.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.21.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.21.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.210.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.210.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.210.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.211.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.211.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.211.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.212.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.212.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.212.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.213.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.213.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.213.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.214.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.214.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.214.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.215.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.215.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.215.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.216.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.216.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.216.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.217.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.217.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.217.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.218.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.218.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.218.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.219.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.219.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.219.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.22.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.22.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.22.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.220.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.220.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.220.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.221.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.221.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.221.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.222.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.222.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.222.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.223.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.223.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.223.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.224.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.224.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.224.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.225.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.225.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.225.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.226.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.226.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.226.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.227.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.227.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.227.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.228.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.228.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.228.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.229.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.229.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.229.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.23.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.23.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.23.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.230.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.230.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.230.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.231.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.231.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.231.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.232.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.232.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.232.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.233.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.233.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.233.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.234.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.234.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.234.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.235.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.235.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.235.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.236.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.236.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.236.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.237.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.237.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.237.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.238.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.238.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.238.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.239.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.239.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.239.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.24.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.24.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.24.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.240.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.240.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.240.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.241.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.241.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.241.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.242.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.242.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.242.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.243.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.243.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.243.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.244.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.244.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.244.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.245.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.245.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.245.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.246.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.246.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.246.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.247.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.247.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.247.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.248.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.248.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.248.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.249.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.249.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.249.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.25.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.25.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.25.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.250.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.250.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.250.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.251.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.251.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.251.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.252.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.252.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.252.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.253.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.253.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.253.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.254.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.254.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.254.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.255.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.255.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.255.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.26.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.26.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.26.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.27.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.27.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.27.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.28.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.28.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.28.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.29.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.29.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.29.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.3.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.3.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.3.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.30.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.30.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.30.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.31.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.31.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.31.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.32.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.32.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.32.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.33.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.33.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.33.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.34.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.34.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.34.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.35.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.35.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.35.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.36.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.36.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.36.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.37.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.37.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.37.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.38.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.38.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.38.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.39.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.39.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.39.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.4.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.4.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.4.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.40.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.40.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.40.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.41.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.41.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.41.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.42.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.42.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.42.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.43.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.43.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.43.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.44.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.44.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.44.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.45.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.45.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.45.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.46.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.46.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.46.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.47.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.47.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.47.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.48.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.48.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.48.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.49.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.49.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.49.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.5.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.5.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.5.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.50.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.50.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.50.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.51.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.51.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.51.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.52.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.52.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.52.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.53.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.53.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.53.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.54.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.54.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.54.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.55.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.55.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.55.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.56.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.56.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.56.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.57.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.57.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.57.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.58.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.58.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.58.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.59.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.59.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.59.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.6.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.6.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.6.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.60.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.60.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.60.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.61.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.61.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.61.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.62.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.62.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.62.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.63.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.63.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.63.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.64.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.64.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.64.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.65.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.65.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.65.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.66.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.66.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.66.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.67.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.67.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.67.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.68.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.68.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.68.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.69.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.69.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.69.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.7.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.7.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.7.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.70.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.70.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.70.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.71.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.71.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.71.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.72.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.72.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.72.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.73.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.73.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.73.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.74.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.74.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.74.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.75.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.75.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.75.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.76.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.76.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.76.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.77.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.77.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.77.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.78.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.78.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.78.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.79.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.79.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.79.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.8.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.8.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.8.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.80.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.80.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.80.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.81.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.81.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.81.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.82.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.82.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.82.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.83.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.83.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.83.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.84.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.84.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.84.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.85.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.85.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.85.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.86.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.86.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.86.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.87.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.87.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.87.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.88.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.88.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.88.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.89.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.89.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.89.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.9.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.9.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.9.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.90.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.90.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.90.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.91.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.91.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.91.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.92.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.92.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.92.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.93.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.93.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.93.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.94.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.94.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.94.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.95.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.95.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.95.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.96.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.96.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.96.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.97.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.97.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.97.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.98.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.98.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.98.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.99.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.99.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.experts.99.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.36.mlp.gate.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00029-of-00033.safetensors", + "model.language_model.layers.36.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.input_layernorm.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.A_log": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.dt_bias": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.norm.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.0.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.0.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.0.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.1.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.1.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.1.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.10.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.10.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.10.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.100.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.100.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.100.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.101.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.101.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.101.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.102.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.102.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.102.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.103.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.103.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.103.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.104.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.104.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.104.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.105.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.105.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.105.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.106.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.106.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.106.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.107.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.107.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.107.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.108.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.108.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.108.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.109.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.109.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.109.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.11.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.11.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.11.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.110.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.110.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.110.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.111.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.111.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.111.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.112.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.112.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.112.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.113.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.113.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.113.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.114.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.114.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.114.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.115.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.115.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.115.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.116.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.116.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.116.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.117.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.117.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.117.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.118.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.118.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.118.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.119.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.119.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.119.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.12.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.12.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.12.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.120.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.120.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.120.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.121.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.121.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.121.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.122.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.122.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.122.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.123.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.123.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.123.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.124.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.124.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.124.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.125.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.125.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.125.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.126.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.126.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.126.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.127.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.127.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.127.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.128.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.128.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.128.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.129.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.129.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.129.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.13.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.13.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.13.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.130.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.130.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.130.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.131.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.131.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.131.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.132.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.132.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.132.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.133.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.133.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.133.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.134.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.134.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.134.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.135.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.135.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.135.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.136.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.136.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.136.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.137.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.137.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.137.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.138.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.138.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.138.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.139.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.139.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.139.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.14.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.14.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.14.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.140.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.140.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.140.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.141.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.141.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.141.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.142.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.142.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.142.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.143.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.143.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.143.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.144.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.144.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.144.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.145.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.145.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.145.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.146.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.146.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.146.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.147.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.147.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.147.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.148.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.148.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.148.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.149.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.149.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.149.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.15.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.15.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.15.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.150.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.150.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.150.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.151.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.151.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.151.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.152.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.152.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.152.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.153.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.153.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.153.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.154.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.154.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.154.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.155.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.155.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.155.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.156.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.156.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.156.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.157.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.157.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.157.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.158.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.158.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.158.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.159.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.159.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.159.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.16.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.16.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.16.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.160.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.160.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.160.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.161.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.161.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.161.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.162.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.162.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.162.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.163.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.163.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.163.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.164.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.164.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.164.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.165.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.165.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.165.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.166.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.166.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.166.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.167.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.167.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.167.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.168.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.168.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.168.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.169.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.169.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.169.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.17.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.17.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.17.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.170.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.170.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.170.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.171.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.171.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.171.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.172.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.172.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.172.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.173.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.173.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.173.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.174.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.174.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.174.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.175.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.175.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.175.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.176.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.176.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.176.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.177.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.177.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.177.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.178.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.178.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.178.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.179.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.179.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.179.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.18.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.18.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.18.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.180.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.180.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.180.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.181.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.181.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.181.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.182.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.182.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.182.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.183.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.183.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.183.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.184.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.184.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.184.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.185.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.185.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.185.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.186.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.186.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.186.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.187.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.187.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.187.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.188.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.188.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.188.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.189.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.189.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.189.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.19.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.19.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.19.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.190.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.190.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.190.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.191.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.191.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.191.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.192.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.192.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.192.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.193.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.193.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.193.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.194.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.194.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.194.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.195.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.195.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.195.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.196.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.196.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.196.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.197.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.197.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.197.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.198.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.198.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.198.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.199.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.199.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.199.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.2.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.2.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.2.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.20.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.20.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.20.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.200.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.200.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.200.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.201.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.201.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.201.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.202.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.202.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.202.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.203.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.203.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.203.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.204.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.204.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.204.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.205.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.205.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.205.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.206.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.206.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.206.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.207.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.207.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.207.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.208.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.208.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.208.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.209.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.209.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.209.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.21.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.21.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.21.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.210.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.210.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.210.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.211.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.211.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.211.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.212.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.212.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.212.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.213.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.213.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.213.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.214.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.214.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.214.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.215.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.215.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.215.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.216.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.216.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.216.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.217.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.217.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.217.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.218.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.218.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.218.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.219.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.219.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.219.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.22.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.22.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.22.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.220.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.220.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.220.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.221.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.221.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.221.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.222.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.222.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.222.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.223.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.223.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.223.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.224.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.224.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.224.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.225.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.225.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.225.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.226.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.226.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.226.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.227.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.227.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.227.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.228.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.228.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.228.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.229.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.229.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.229.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.23.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.23.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.23.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.230.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.230.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.230.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.231.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.231.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.231.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.232.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.232.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.232.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.233.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.233.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.233.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.234.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.234.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.234.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.235.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.235.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.235.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.236.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.236.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.236.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.237.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.237.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.237.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.238.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.238.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.238.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.239.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.239.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.239.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.24.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.24.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.24.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.240.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.240.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.240.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.241.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.241.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.241.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.242.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.242.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.242.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.243.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.243.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.243.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.244.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.244.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.244.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.245.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.245.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.245.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.246.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.246.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.246.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.247.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.247.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.247.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.248.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.248.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.248.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.249.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.249.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.249.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.25.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.25.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.25.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.250.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.250.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.250.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.251.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.251.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.251.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.252.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.252.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.252.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.253.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.253.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.253.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.254.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.254.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.254.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.255.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.255.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.255.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.26.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.26.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.26.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.27.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.27.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.27.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.28.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.28.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.28.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.29.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.29.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.29.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.3.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.3.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.3.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.30.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.30.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.30.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.31.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.31.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.31.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.32.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.32.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.32.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.33.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.33.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.33.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.34.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.34.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.34.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.35.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.35.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.35.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.36.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.36.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.36.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.37.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.37.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.37.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.38.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.38.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.38.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.39.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.39.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.39.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.4.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.4.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.4.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.40.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.40.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.40.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.41.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.41.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.41.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.42.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.42.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.42.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.43.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.43.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.43.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.44.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.44.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.44.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.45.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.45.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.45.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.46.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.46.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.46.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.47.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.47.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.47.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.48.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.48.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.48.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.49.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.49.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.49.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.5.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.5.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.5.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.50.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.50.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.50.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.51.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.51.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.51.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.52.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.52.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.52.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.53.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.53.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.53.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.54.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.54.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.54.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.55.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.55.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.55.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.56.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.56.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.56.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.57.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.57.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.57.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.58.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.58.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.58.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.59.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.59.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.59.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.6.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.6.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.6.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.60.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.60.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.60.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.61.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.61.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.61.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.62.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.62.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.62.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.63.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.63.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.63.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.64.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.64.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.64.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.65.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.65.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.65.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.66.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.66.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.66.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.67.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.67.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.67.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.68.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.68.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.68.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.69.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.69.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.69.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.7.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.7.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.7.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.70.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.70.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.70.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.71.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.71.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.71.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.72.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.72.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.72.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.73.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.73.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.73.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.74.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.74.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.74.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.75.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.75.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.75.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.76.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.76.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.76.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.77.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.77.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.77.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.78.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.78.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.78.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.79.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.79.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.79.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.8.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.8.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.8.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.80.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.80.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.80.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.81.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.81.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.81.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.82.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.82.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.82.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.83.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.83.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.83.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.84.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.84.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.84.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.85.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.85.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.85.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.86.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.86.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.86.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.87.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.87.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.87.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.88.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.88.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.88.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.89.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.89.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.89.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.9.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.9.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.9.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.90.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.90.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.90.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.91.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.91.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.91.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.92.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.92.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.92.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.93.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.93.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.93.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.94.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.94.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.94.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.95.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.95.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.95.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.96.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.96.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.96.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.97.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.97.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.97.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.98.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.98.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.98.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.99.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.99.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.experts.99.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.gate.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00030-of-00033.safetensors", + "model.language_model.layers.37.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.input_layernorm.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.A_log": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.dt_bias": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.norm.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.0.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.0.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.0.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.1.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.1.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.1.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.10.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.10.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.10.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.100.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.100.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.100.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.101.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.101.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.101.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.102.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.102.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.102.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.103.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.103.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.103.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.104.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.104.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.104.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.105.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.105.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.105.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.106.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.106.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.106.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.107.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.107.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.107.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.108.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.108.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.108.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.109.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.109.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.109.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.11.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.11.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.11.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.110.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.110.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.110.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.111.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.111.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.111.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.112.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.112.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.112.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.113.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.113.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.113.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.114.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.114.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.114.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.115.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.115.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.115.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.116.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.116.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.116.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.117.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.117.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.117.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.118.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.118.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.118.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.119.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.119.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.119.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.12.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.12.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.12.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.120.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.120.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.120.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.121.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.121.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.121.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.122.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.122.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.122.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.123.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.123.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.123.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.124.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.124.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.124.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.125.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.125.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.125.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.126.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.126.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.126.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.127.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.127.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.127.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.128.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.128.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.128.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.129.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.129.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.129.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.13.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.13.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.13.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.130.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.130.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.130.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.131.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.131.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.131.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.132.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.132.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.132.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.133.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.133.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.133.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.134.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.134.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.134.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.135.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.135.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.135.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.136.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.136.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.136.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.137.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.137.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.137.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.138.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.138.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.138.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.139.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.139.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.139.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.14.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.14.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.14.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.140.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.140.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.140.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.141.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.141.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.141.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.142.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.142.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.142.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.143.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.143.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.143.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.144.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.144.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.144.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.145.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.145.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.145.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.146.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.146.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.146.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.147.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.147.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.147.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.148.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.148.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.148.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.149.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.149.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.149.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.15.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.15.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.15.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.150.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.150.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.150.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.151.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.151.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.151.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.152.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.152.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.152.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.153.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.153.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.153.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.154.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.154.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.154.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.155.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.155.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.155.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.156.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.156.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.156.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.157.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.157.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.157.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.158.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.158.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.158.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.159.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.159.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.159.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.16.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.16.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.16.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.160.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.160.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.160.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.161.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.161.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.161.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.162.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.162.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.162.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.163.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.163.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.163.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.164.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.164.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.164.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.165.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.165.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.165.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.166.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.166.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.166.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.167.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.167.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.167.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.168.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.168.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.168.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.169.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.169.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.169.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.17.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.17.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.17.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.170.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.170.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.170.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.171.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.171.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.171.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.172.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.172.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.172.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.173.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.173.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.173.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.174.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.174.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.174.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.175.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.175.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.175.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.176.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.176.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.176.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.177.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.177.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.177.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.178.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.178.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.178.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.179.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.179.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.179.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.18.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.18.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.18.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.180.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.180.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.180.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.181.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.181.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.181.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.182.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.182.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.182.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.183.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.183.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.183.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.184.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.184.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.184.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.185.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.185.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.185.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.186.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.186.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.186.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.187.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.187.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.187.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.188.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.188.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.188.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.189.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.189.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.189.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.19.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.19.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.19.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.190.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.190.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.190.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.191.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.191.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.191.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.192.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.192.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.192.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.193.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.193.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.193.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.194.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.194.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.194.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.195.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.195.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.195.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.196.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.196.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.196.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.197.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.197.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.197.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.198.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.198.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.198.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.199.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.199.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.199.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.2.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.2.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.2.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.20.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.20.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.20.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.200.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.200.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.200.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.201.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.201.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.201.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.202.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.202.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.202.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.203.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.203.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.203.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.204.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.204.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.204.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.205.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.205.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.205.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.206.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.206.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.206.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.207.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.207.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.207.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.208.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.208.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.208.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.209.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.209.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.209.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.21.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.21.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.21.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.210.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.210.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.210.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.211.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.211.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.211.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.212.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.212.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.212.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.213.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.213.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.213.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.214.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.214.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.214.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.215.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.215.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.215.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.216.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.216.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.216.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.217.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.217.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.217.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.218.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.218.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.218.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.219.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.219.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.219.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.22.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.22.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.22.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.220.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.220.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.220.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.221.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.221.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.221.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.222.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.222.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.222.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.223.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.223.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.223.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.224.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.224.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.224.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.225.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.225.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.225.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.226.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.226.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.226.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.227.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.227.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.227.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.228.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.228.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.228.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.229.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.229.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.229.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.23.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.23.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.23.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.230.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.230.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.230.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.231.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.231.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.231.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.232.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.232.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.232.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.233.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.233.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.233.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.234.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.234.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.234.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.235.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.235.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.235.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.236.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.236.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.236.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.237.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.237.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.237.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.238.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.238.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.238.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.239.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.239.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.239.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.24.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.24.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.24.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.240.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.240.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.240.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.241.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.241.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.241.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.242.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.242.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.242.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.243.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.243.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.243.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.244.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.244.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.244.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.245.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.245.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.245.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.246.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.246.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.246.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.247.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.247.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.247.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.248.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.248.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.248.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.249.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.249.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.249.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.25.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.25.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.25.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.250.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.250.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.250.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.251.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.251.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.251.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.252.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.252.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.252.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.253.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.253.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.253.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.254.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.254.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.254.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.255.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.255.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.255.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.26.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.26.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.26.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.27.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.27.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.27.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.28.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.28.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.28.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.29.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.29.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.29.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.3.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.3.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.3.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.30.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.30.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.30.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.31.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.31.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.31.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.32.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.32.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.32.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.33.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.33.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.33.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.34.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.34.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.34.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.35.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.35.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.35.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.36.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.36.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.36.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.37.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.37.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.37.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.38.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.38.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.38.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.39.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.39.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.39.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.4.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.4.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.4.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.40.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.40.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.40.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.41.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.41.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.41.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.42.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.42.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.42.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.43.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.43.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.43.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.44.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.44.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.44.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.45.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.45.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.45.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.46.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.46.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.46.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.47.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.47.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.47.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.48.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.48.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.48.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.49.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.49.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.49.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.5.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.5.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.5.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.50.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.50.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.50.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.51.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.51.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.51.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.52.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.52.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.52.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.53.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.53.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.53.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.54.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.54.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.54.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.55.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.55.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.55.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.56.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.56.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.56.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.57.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.57.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.57.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.58.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.58.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.58.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.59.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.59.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.59.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.6.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.6.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.6.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.60.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.60.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.60.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.61.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.61.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.61.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.62.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.62.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.62.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.63.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.63.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.63.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.64.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.64.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.64.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.65.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.65.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.65.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.66.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.66.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.66.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.67.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.67.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.67.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.68.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.68.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.68.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.69.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.69.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.69.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.7.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.7.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.7.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.70.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.70.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.70.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.71.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.71.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.71.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.72.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.72.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.72.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.73.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.73.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.73.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.74.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.74.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.74.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.75.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.75.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.75.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.76.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.76.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.76.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.77.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.77.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.77.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.78.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.78.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.78.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.79.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.79.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.79.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.8.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.8.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.8.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.80.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.80.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.80.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.81.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.81.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.81.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.82.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.82.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.82.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.83.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.83.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.83.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.84.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.84.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.84.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.85.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.85.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.85.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.86.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.86.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.86.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.87.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.87.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.87.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.88.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.88.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.88.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.89.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.89.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.89.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.9.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.9.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.9.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.90.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.90.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.90.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.91.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.91.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.91.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.92.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.92.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.92.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.93.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.93.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.93.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.94.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.94.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.94.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.95.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.95.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.95.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.96.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.96.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.96.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.97.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.97.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.97.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.98.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.98.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.98.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.99.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.99.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.experts.99.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.38.mlp.gate.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.38.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", + "model.language_model.layers.39.input_layernorm.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.0.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.0.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.0.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.1.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.1.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.1.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.10.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.10.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.10.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.100.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.100.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.100.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.101.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.101.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.101.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.102.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.102.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.102.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.103.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.103.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.103.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.104.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.104.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.104.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.105.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.105.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.105.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.106.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.106.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.106.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.107.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.107.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.107.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.108.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.108.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.108.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.109.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.109.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.109.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.11.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.11.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.11.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.110.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.110.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.110.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.111.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.111.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.111.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.112.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.112.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.112.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.113.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.113.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.113.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.114.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.114.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.114.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.115.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.115.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.115.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.116.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.116.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.116.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.117.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.117.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.117.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.118.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.118.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.118.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.119.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.119.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.119.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.12.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.12.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.12.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.120.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.120.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.120.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.121.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.121.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.121.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.122.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.122.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.122.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.123.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.123.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.123.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.124.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.124.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.124.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.125.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.125.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.125.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.126.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.126.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.126.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.127.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.127.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.127.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.128.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.128.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.128.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.129.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.129.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.129.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.13.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.13.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.13.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.130.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.130.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.130.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.131.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.131.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.131.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.132.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.132.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.132.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.133.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.133.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.133.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.134.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.134.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.134.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.135.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.135.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.135.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.136.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.136.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.136.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.137.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.137.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.137.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.138.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.138.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.138.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.139.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.139.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.139.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.14.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.14.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.14.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.140.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.140.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.140.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.141.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.141.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.141.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.142.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.142.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.142.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.143.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.143.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.143.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.144.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.144.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.144.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.145.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.145.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.145.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.146.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.146.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.146.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.147.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.147.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.147.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.148.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.148.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.148.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.149.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.149.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.149.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.15.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.15.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.15.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.150.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.150.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.150.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.151.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.151.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.151.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.152.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.152.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.152.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.153.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.153.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.153.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.154.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.154.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.154.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.155.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.155.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.155.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.156.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.156.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.156.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.157.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.157.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.157.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.158.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.158.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.158.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.159.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.159.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.159.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.16.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.16.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.16.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.160.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.160.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.160.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.161.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.161.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.161.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.162.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.162.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.162.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.163.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.163.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.163.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.164.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.164.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.164.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.165.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.165.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.165.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.166.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.166.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.166.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.167.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.167.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.167.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.168.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.168.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.168.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.169.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.169.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.169.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.17.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.17.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.17.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.170.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.170.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.170.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.171.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.171.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.171.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.172.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.172.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.172.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.173.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.173.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.173.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.174.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.174.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.174.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.175.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.175.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.175.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.176.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.176.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.176.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.177.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.177.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.177.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.178.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.178.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.178.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.179.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.179.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.179.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.18.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.18.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.18.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.180.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.180.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.180.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.181.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.181.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.181.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.182.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.182.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.182.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.183.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.183.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.183.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.184.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.184.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.184.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.185.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.185.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.185.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.186.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.186.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.186.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.187.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.187.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.187.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.188.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.188.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.188.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.189.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.189.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.189.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.19.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.19.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.19.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.190.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.190.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.190.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.191.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.191.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.191.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.192.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.192.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.192.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.193.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.193.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.193.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.194.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.194.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.194.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.195.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.195.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.195.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.196.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.196.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.196.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.197.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.197.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.197.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.198.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.198.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.198.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.199.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.199.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.199.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.2.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.2.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.2.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.20.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.20.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.20.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.200.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.200.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.200.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.201.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.201.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.201.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.202.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.202.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.202.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.203.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.203.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.203.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.204.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.204.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.204.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.205.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.205.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.205.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.206.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.206.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.206.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.207.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.207.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.207.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.208.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.208.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.208.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.209.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.209.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.209.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.21.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.21.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.21.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.210.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.210.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.210.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.211.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.211.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.211.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.212.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.212.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.212.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.213.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.213.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.213.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.214.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.214.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.214.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.215.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.215.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.215.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.216.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.216.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.216.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.217.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.217.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.217.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.218.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.218.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.218.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.219.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.219.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.219.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.22.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.22.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.22.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.220.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.220.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.220.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.221.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.221.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.221.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.222.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.222.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.222.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.223.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.223.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.223.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.224.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.224.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.224.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.225.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.225.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.225.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.226.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.226.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.226.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.227.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.227.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.227.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.228.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.228.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.228.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.229.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.229.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.229.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.23.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.23.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.23.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.230.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.230.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.230.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.231.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.231.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.231.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.232.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.232.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.232.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.233.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.233.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.233.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.234.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.234.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.234.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.235.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.235.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.235.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.236.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.236.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.236.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.237.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.237.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.237.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.238.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.238.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.238.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.239.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.239.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.239.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.24.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.24.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.24.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.240.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.240.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.240.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.241.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.241.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.241.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.242.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.242.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.242.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.243.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.243.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.243.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.244.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.244.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.244.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.245.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.245.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.245.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.246.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.246.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.246.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.247.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.247.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.247.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.248.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.248.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.248.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.249.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.249.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.249.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.25.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.25.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.25.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.250.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.250.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.250.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.251.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.251.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.251.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.252.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.252.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.252.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.253.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.253.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.253.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.254.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.254.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.254.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.255.down_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.255.gate_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.255.up_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.26.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.26.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.26.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.27.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.27.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.27.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.28.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.28.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.28.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.29.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.29.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.29.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.3.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.3.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.3.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.30.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.30.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.30.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.31.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.31.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.31.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.32.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.32.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.32.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.33.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.33.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.33.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.34.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.34.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.34.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.35.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.35.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.35.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.36.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.36.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.36.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.37.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.37.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.37.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.38.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.38.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.38.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.39.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.39.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.39.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.4.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.4.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.4.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.40.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.40.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.40.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.41.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.41.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.41.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.42.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.42.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.42.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.43.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.43.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.43.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.44.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.44.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.44.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.45.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.45.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.45.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.46.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.46.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.46.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.47.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.47.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.47.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.48.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.48.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.48.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.49.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.49.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.49.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.5.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.5.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.5.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.50.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.50.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.50.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.51.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.51.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.51.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.52.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.52.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.52.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.53.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.53.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.53.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.54.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.54.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.54.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.55.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.55.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.55.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.56.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.56.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.56.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.57.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.57.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.57.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.58.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.58.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.58.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.59.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.59.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.59.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.6.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.6.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.6.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.60.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.60.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.60.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.61.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.61.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.61.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.62.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.62.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.62.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.63.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.63.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.63.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.64.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.64.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.64.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.65.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.65.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.65.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.66.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.66.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.66.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.67.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.67.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.67.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.68.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.68.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.68.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.69.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.69.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.69.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.7.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.7.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.7.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.70.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.70.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.70.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.71.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.71.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.71.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.72.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.72.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.72.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.73.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.73.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.73.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.74.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.74.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.74.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.75.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.75.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.75.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.76.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.76.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.76.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.77.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.77.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.77.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.78.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.78.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.78.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.79.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.79.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.79.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.8.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.8.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.8.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.80.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.80.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.80.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.81.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.81.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.81.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.82.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.82.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.82.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.83.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.83.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.83.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.84.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.84.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.84.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.85.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.85.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.85.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.86.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.86.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.86.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.87.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.87.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.87.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.88.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.88.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.88.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.89.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.89.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.89.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.9.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.9.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.9.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.90.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.90.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.90.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.91.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.91.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.91.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.92.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.92.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.92.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.93.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.93.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.93.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.94.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.94.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.94.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.95.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.95.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.95.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.96.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.96.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.96.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.97.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.97.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.97.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.98.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.98.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.98.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.99.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.99.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.experts.99.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.gate.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00032-of-00033.safetensors", + "model.language_model.layers.39.post_attention_layernorm.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.self_attn.k_norm.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.self_attn.k_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.self_attn.q_norm.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.39.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.A_log": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.dt_bias": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.norm.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.0.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.0.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.0.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.1.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.1.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.1.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.10.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.10.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.100.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.100.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.100.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.101.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.101.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.101.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.102.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.102.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.102.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.103.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.103.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.103.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.104.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.104.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.104.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.105.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.105.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.105.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.106.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.106.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.106.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.107.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.107.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.107.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.108.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.108.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.108.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.109.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.109.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.109.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.11.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.11.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.11.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.110.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.110.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.110.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.111.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.111.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.111.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.112.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.112.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.112.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.113.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.113.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.113.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.114.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.114.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.114.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.115.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.115.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.115.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.116.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.116.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.116.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.117.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.117.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.117.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.118.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.118.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.118.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.119.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.119.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.119.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.12.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.12.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.12.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.120.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.120.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.120.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.121.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.121.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.128.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.128.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.128.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.129.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.129.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.129.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.13.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.13.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.13.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.130.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.130.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.130.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.131.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.131.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.131.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.132.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.132.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.132.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.133.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.133.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.133.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.134.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.134.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.134.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.135.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.135.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.135.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.136.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.136.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.136.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.137.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.137.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.137.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.138.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.138.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.138.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.139.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.139.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.139.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.14.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.14.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.14.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.140.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.140.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.140.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.141.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.141.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.141.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.142.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.142.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.142.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.143.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.143.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.143.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.144.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.144.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.144.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.145.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.145.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.145.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.146.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.146.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.146.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.147.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.147.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.147.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.148.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.148.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.148.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.149.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.149.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.149.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.15.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.15.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.15.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.150.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.150.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.150.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.151.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.151.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.151.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.152.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.152.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.152.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.153.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.153.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.153.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.154.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.154.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.154.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.155.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.155.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.155.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.156.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.156.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.156.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.157.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.157.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.157.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.158.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.158.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.158.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.159.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.159.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.159.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.16.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.16.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.16.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.160.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.160.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.160.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.161.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.161.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.161.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.162.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.162.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.162.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.163.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.163.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.163.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.164.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.164.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.164.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.165.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.165.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.165.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.166.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.166.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.166.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.167.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.167.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.167.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.168.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.168.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.168.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.169.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.169.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.169.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.17.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.17.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.17.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.170.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.170.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.170.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.171.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.171.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.171.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.172.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.172.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.172.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.173.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.173.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.173.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.174.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.174.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.174.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.175.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.175.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.175.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.176.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.176.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.176.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.177.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.177.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.177.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.178.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.178.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.178.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.179.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.179.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.179.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.18.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.18.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.18.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.180.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.180.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.180.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.181.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.181.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.181.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.182.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.182.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.182.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.183.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.183.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.183.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.184.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.184.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.184.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.185.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.185.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.185.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.186.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.186.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.186.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.187.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.187.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.187.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.188.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.188.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.188.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.189.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.189.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.189.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.19.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.19.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.190.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.190.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.190.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.191.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.191.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.191.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.192.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.192.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.192.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.193.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.193.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.193.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.194.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.194.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.194.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.195.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.195.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.195.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.196.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.196.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.196.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.197.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.197.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.197.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.198.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.198.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.198.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.199.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.199.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.199.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.2.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.2.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.2.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.20.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.20.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.20.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.200.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.200.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.200.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.201.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.201.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.201.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.202.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.202.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.202.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.203.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.203.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.203.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.204.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.204.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.204.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.205.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.205.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.205.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.206.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.206.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.206.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.207.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.207.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.207.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.208.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.208.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.208.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.209.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.209.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.209.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.21.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.21.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.21.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.210.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.210.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.210.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.211.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.211.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.211.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.212.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.212.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.212.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.213.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.213.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.213.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.214.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.214.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.214.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.215.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.215.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.215.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.216.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.216.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.216.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.217.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.217.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.217.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.218.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.218.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.218.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.219.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.219.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.219.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.22.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.22.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.22.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.220.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.220.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.220.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.221.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.221.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.221.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.222.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.222.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.222.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.223.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.223.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.223.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.224.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.224.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.224.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.225.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.225.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.225.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.226.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.226.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.226.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.227.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.227.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.227.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.228.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.228.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.228.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.229.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.229.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.229.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.23.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.23.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.23.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.230.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.230.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.230.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.231.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.231.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.231.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.232.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.232.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.232.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.233.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.233.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.233.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.234.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.234.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.234.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.235.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.235.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.235.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.236.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.236.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.236.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.237.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.237.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.237.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.238.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.238.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.238.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.239.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.239.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.239.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.24.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.24.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.24.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.240.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.240.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.240.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.241.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.241.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.241.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.242.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.242.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.242.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.243.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.243.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.243.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.244.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.244.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.244.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.245.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.245.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.245.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.246.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.246.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.246.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.247.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.247.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.247.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.248.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.248.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.248.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.249.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.249.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.249.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.25.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.25.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.25.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.250.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.250.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.250.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.251.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.251.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.251.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.252.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.252.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.252.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.253.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.253.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.253.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.254.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.254.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.254.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.255.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.255.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.255.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.26.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.26.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.26.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.27.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.27.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.28.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.28.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.28.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.29.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.29.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.29.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.3.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.3.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.3.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.30.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.30.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.30.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.31.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.31.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.32.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.32.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.32.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.33.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.33.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.33.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.34.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.34.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.34.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.35.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.35.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.35.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.36.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.36.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.36.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.37.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.37.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.37.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.38.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.38.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.38.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.39.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.39.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.39.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.4.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.4.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.4.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.40.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.40.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.40.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.41.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.41.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.42.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.42.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.43.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.43.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.43.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.44.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.44.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.44.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.45.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.45.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.45.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.46.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.46.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.46.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.47.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.47.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.47.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.48.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.48.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.48.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.49.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.49.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.49.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.5.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.5.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.5.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.50.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.50.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.50.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.51.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.51.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.52.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.52.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.52.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.53.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.53.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.54.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.54.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.54.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.55.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.55.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.55.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.56.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.56.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.56.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.57.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.57.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.57.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.58.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.58.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.58.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.59.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.59.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.59.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.6.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.6.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.6.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.60.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.60.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.60.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.61.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.61.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.61.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.62.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.62.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.62.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.63.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.63.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.63.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.64.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.64.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.64.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.65.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.65.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.65.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.66.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.66.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.66.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.67.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.67.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.67.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.68.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.68.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.68.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.69.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.69.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.69.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.7.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.7.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.7.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.70.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.70.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.70.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.71.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.71.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.71.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.72.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.72.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.72.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.73.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.73.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.73.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.74.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.74.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.74.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.75.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.75.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.75.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.76.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.76.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.76.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.77.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.77.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.77.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.78.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.78.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.78.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.79.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.79.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.79.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.8.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.8.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.8.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.80.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.80.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.80.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.81.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.81.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.81.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.82.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.82.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.82.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.83.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.83.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.83.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.84.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.84.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.84.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.85.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.85.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.85.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.86.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.86.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.86.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.87.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.87.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.87.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.88.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.88.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.88.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.89.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.89.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.89.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.9.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.9.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.9.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.90.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.90.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.90.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.91.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.91.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.91.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.92.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.92.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.92.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.93.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.93.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.93.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.94.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.94.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.94.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.95.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.95.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.95.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.96.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.96.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.96.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.97.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.97.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.97.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.98.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.98.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.98.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.99.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.99.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.experts.99.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.gate.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00004-of-00033.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.A_log": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.dt_bias": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.norm.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.0.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.0.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.0.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.1.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.1.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.1.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.10.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.10.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.10.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.100.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.100.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.100.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.101.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.101.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.101.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.102.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.102.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.102.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.103.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.103.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.103.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.104.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.104.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.104.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.105.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.105.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.105.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.106.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.106.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.106.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.107.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.107.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.107.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.108.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.108.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.108.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.109.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.109.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.109.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.11.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.11.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.11.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.110.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.110.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.110.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.111.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.111.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.111.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.112.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.112.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.112.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.113.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.113.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.113.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.114.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.114.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.114.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.115.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.115.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.115.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.116.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.116.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.116.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.117.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.117.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.117.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.118.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.118.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.118.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.119.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.119.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.119.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.12.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.12.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.12.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.120.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.120.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.120.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.121.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.121.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.121.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.122.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.122.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.122.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.123.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.123.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.123.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.124.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.124.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.124.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.125.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.125.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.125.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.126.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.126.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.126.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.127.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.127.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.127.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.128.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.128.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.128.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.129.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.129.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.129.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.13.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.13.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.13.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.130.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.130.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.130.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.131.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.131.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.131.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.132.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.132.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.132.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.133.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.133.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.133.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.134.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.134.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.134.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.135.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.135.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.135.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.136.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.136.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.136.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.137.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.137.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.137.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.138.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.138.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.138.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.139.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.139.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.139.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.14.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.14.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.14.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.140.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.140.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.140.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.141.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.141.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.141.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.142.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.142.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.142.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.143.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.143.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.143.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.144.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.144.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.144.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.145.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.145.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.145.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.146.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.146.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.146.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.147.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.147.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.147.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.148.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.148.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.148.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.149.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.149.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.149.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.15.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.15.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.15.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.150.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.150.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.150.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.151.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.151.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.151.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.152.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.152.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.152.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.153.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.153.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.153.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.154.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.154.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.154.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.155.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.155.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.155.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.156.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.156.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.156.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.157.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.157.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.157.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.158.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.158.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.158.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.159.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.159.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.159.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.16.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.16.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.16.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.160.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.160.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.160.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.161.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.161.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.161.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.162.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.162.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.162.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.163.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.163.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.163.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.164.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.164.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.164.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.165.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.165.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.165.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.166.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.166.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.166.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.167.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.167.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.167.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.168.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.168.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.168.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.169.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.169.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.169.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.17.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.17.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.17.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.170.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.170.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.170.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.171.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.171.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.171.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.172.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.172.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.172.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.173.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.173.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.173.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.174.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.174.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.174.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.175.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.175.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.175.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.176.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.176.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.176.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.177.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.177.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.177.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.178.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.178.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.178.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.179.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.179.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.179.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.18.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.18.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.18.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.180.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.180.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.180.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.181.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.181.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.181.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.182.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.182.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.182.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.183.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.183.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.183.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.184.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.184.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.184.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.185.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.185.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.185.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.186.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.186.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.186.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.187.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.187.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.187.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.188.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.188.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.188.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.189.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.189.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.189.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.19.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.19.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.19.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.190.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.190.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.190.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.191.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.191.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.191.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.192.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.192.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.192.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.193.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.193.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.193.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.194.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.194.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.194.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.195.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.195.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.195.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.196.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.196.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.196.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.197.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.197.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.197.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.198.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.198.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.198.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.199.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.199.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.199.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.2.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.2.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.2.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.20.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.20.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.20.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.200.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.200.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.200.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.201.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.201.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.201.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.202.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.202.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.202.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.203.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.203.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.203.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.204.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.204.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.204.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.205.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.205.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.205.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.206.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.206.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.206.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.207.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.207.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.207.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.208.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.208.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.208.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.209.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.209.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.209.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.21.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.21.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.21.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.210.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.210.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.210.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.211.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.211.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.211.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.212.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.212.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.212.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.213.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.213.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.213.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.214.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.214.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.214.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.215.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.215.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.215.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.216.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.216.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.216.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.217.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.217.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.217.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.218.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.218.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.218.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.219.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.219.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.219.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.22.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.22.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.22.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.220.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.220.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.220.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.221.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.221.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.221.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.222.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.222.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.222.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.223.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.223.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.223.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.224.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.224.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.224.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.225.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.225.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.225.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.226.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.226.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.226.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.227.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.227.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.227.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.228.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.228.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.228.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.229.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.229.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.229.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.23.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.23.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.23.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.230.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.230.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.230.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.231.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.231.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.231.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.232.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.232.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.232.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.233.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.233.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.233.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.234.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.234.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.234.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.235.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.235.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.235.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.236.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.236.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.236.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.237.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.237.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.237.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.238.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.238.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.238.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.239.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.239.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.239.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.24.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.24.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.24.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.240.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.240.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.240.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.241.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.241.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.241.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.242.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.242.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.242.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.243.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.243.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.243.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.244.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.244.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.244.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.245.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.245.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.245.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.246.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.246.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.246.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.247.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.247.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.247.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.248.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.248.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.248.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.249.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.249.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.249.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.25.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.25.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.25.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.250.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.250.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.250.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.251.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.251.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.251.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.252.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.252.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.252.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.253.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.253.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.253.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.254.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.254.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.254.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.255.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.255.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.255.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.26.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.26.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.26.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.27.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.27.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.27.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.28.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.28.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.28.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.29.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.29.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.29.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.3.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.3.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.3.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.30.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.30.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.30.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.31.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.31.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.31.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.32.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.32.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.32.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.33.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.33.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.33.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.34.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.34.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.34.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.35.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.35.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.35.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.36.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.36.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.36.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.37.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.37.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.37.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.38.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.38.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.38.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.39.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.39.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.39.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.4.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.4.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.4.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.40.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.40.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.40.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.41.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.41.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.41.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.42.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.42.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.42.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.43.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.43.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.43.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.44.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.44.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.44.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.45.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.45.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.45.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.46.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.46.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.46.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.47.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.47.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.47.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.48.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.48.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.48.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.49.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.49.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.49.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.5.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.5.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.5.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.50.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.50.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.50.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.51.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.51.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.51.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.52.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.52.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.52.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.53.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.53.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.53.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.54.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.54.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.54.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.55.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.55.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.55.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.56.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.56.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.56.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.57.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.57.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.57.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.58.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.58.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.58.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.59.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.59.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.59.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.6.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.6.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.6.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.60.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.60.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.60.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.61.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.61.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.61.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.62.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.62.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.62.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.63.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.63.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.63.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.64.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.64.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.64.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.65.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.65.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.65.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.66.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.66.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.66.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.67.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.67.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.67.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.68.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.68.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.68.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.69.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.69.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.69.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.7.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.7.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.7.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.70.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.70.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.70.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.71.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.71.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.71.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.72.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.72.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.72.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.73.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.73.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.73.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.74.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.74.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.74.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.75.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.75.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.75.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.76.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.76.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.76.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.77.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.77.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.77.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.78.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.78.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.78.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.79.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.79.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.79.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.8.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.8.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.8.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.80.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.80.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.80.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.81.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.81.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.81.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.82.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.82.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.82.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.83.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.83.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.83.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.84.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.84.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.84.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.85.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.85.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.85.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.86.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.86.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.86.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.87.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.87.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.87.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.88.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.88.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.88.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.89.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.89.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.89.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.9.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.9.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.9.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.90.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.90.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.90.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.91.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.91.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.91.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.92.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.92.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.92.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.93.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.93.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.93.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.94.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.94.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.94.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.95.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.95.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.95.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.96.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.96.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.96.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.97.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.97.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.97.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.98.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.98.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.98.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.99.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.99.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.experts.99.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.gate.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.A_log": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.dt_bias": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.norm.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.0.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.0.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.0.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.1.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.1.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.1.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.10.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.10.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.10.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.100.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.100.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.100.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.101.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.101.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.101.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.102.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.102.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.102.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.103.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.103.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.103.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.104.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.104.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.104.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.105.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.105.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.105.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.106.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.106.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.106.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.107.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.107.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.107.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.108.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.108.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.108.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.109.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.109.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.109.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.11.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.11.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.11.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.110.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.110.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.110.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.111.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.111.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.111.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.112.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.112.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.112.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.113.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.113.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.113.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.114.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.114.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.114.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.115.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.115.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.115.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.116.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.116.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.116.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.117.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.117.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.117.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.118.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.118.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.118.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.119.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.119.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.119.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.12.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.12.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.12.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.120.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.120.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.120.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.121.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.121.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.121.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.122.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.122.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.122.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.123.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.123.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.123.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.124.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.124.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.124.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.125.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.125.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.125.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.126.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.126.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.126.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.127.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.127.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.127.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.128.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.128.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.128.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.129.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.129.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.129.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.13.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.13.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.13.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.130.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.130.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.130.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.131.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.131.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.131.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.132.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.132.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.132.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.133.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.133.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.133.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.134.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.134.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.134.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.135.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.135.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.135.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.136.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.136.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.136.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.137.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.137.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.137.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.138.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.138.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.138.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.139.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.139.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.139.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.14.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.14.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.14.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.140.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.140.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.140.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.141.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.141.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.141.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.142.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.142.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.142.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.143.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.143.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.143.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.144.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.144.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.144.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.145.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.145.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.145.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.146.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.146.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.146.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.147.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.147.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.147.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.148.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.148.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.148.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.149.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.149.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.149.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.15.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.15.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.15.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.150.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.150.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.150.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.151.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.151.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.151.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.152.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.152.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.152.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.153.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.153.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.153.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.154.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.154.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.154.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.155.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.155.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.155.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.156.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.156.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.156.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.157.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.157.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.157.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.158.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.158.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.158.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.159.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.159.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.159.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.16.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.16.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.16.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.160.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.160.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.160.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.161.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.161.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.161.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.162.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.162.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.162.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.163.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.163.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.163.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.164.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.164.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.164.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.165.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.165.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.165.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.166.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.166.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.166.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.167.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.167.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.167.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.168.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.168.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.168.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.169.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.169.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.169.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.17.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.17.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.17.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.170.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.170.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.170.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.171.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.171.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.171.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.172.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.172.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.172.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.173.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.173.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.173.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.174.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.174.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.174.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.175.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.175.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.175.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.176.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.176.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.176.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.177.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.177.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.177.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.178.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.178.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.178.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.179.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.179.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.179.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.18.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.18.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.18.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.180.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.180.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.180.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.181.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.181.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.181.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.182.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.182.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.182.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.183.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.183.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.183.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.184.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.184.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.184.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.185.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.185.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.185.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.186.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.186.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.186.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.187.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.187.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.187.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.188.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.188.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.188.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.189.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.189.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.189.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.19.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.19.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.19.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.190.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.190.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.190.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.191.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.191.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.191.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.192.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.192.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.192.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.193.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.193.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.193.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.194.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.194.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.194.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.195.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.195.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.195.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.196.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.196.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.196.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.197.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.197.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.197.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.198.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.198.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.198.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.199.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.199.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.199.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.2.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.2.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.2.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.20.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.20.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.20.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.200.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.200.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.200.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.201.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.201.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.201.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.202.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.202.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.202.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.203.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.203.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.203.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.204.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.204.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.204.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.205.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.205.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.205.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.206.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.206.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.206.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.207.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.207.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.207.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.208.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.208.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.208.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.209.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.209.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.209.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.21.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.21.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.21.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.210.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.210.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.210.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.211.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.211.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.211.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.212.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.212.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.212.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.213.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.213.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.213.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.214.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.214.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.214.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.215.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.215.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.215.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.216.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.216.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.216.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.217.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.217.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.217.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.218.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.218.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.218.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.219.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.219.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.219.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.22.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.22.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.22.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.220.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.220.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.220.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.221.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.221.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.221.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.222.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.222.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.222.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.223.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.223.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.223.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.224.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.224.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.224.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.225.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.225.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.225.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.226.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.226.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.226.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.227.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.227.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.227.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.228.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.228.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.228.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.229.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.229.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.229.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.23.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.23.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.23.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.230.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.230.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.230.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.231.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.231.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.231.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.232.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.232.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.232.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.233.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.233.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.233.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.234.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.234.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.234.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.235.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.235.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.235.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.236.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.236.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.236.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.237.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.237.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.237.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.238.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.238.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.238.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.239.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.239.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.239.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.24.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.24.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.24.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.240.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.240.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.240.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.241.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.241.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.241.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.242.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.242.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.242.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.243.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.243.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.243.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.244.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.244.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.244.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.245.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.245.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.245.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.246.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.246.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.246.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.247.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.247.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.247.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.248.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.248.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.248.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.249.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.249.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.249.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.25.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.25.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.25.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.250.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.250.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.250.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.251.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.251.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.251.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.252.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.252.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.252.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.253.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.253.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.253.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.254.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.254.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.254.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.255.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.255.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.255.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.26.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.26.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.26.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.27.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.27.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.27.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.28.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.28.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.28.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.29.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.29.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.29.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.3.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.3.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.3.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.30.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.30.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.30.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.31.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.31.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.31.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.32.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.32.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.32.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.33.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.33.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.33.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.34.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.34.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.34.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.35.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.35.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.35.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.36.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.36.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.36.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.37.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.37.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.37.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.38.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.38.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.38.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.39.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.39.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.39.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.4.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.4.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.4.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.40.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.40.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.40.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.41.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.41.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.41.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.42.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.42.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.42.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.43.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.43.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.43.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.44.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.44.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.44.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.45.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.45.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.45.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.46.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.46.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.46.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.47.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.47.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.47.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.48.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.48.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.48.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.49.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.49.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.49.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.5.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.5.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.5.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.50.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.50.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.50.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.51.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.51.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.51.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.52.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.52.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.52.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.53.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.53.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.53.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.54.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.54.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.54.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.55.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.55.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.55.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.56.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.56.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.56.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.57.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.57.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.57.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.58.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.58.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.58.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.59.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.59.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.59.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.6.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.6.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.6.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.60.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.60.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.60.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.61.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.61.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.61.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.62.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.62.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.62.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.63.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.63.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.63.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.64.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.64.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.64.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.65.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.65.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.65.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.66.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.66.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.66.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.67.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.67.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.67.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.68.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.68.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.68.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.69.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.69.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.69.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.7.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.7.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.7.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.70.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.70.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.70.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.71.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.71.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.71.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.72.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.72.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.72.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.73.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.73.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.73.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.74.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.74.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.74.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.75.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.75.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.75.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.76.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.76.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.76.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.77.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.77.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.77.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.78.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.78.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.78.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.79.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.79.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.79.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.8.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.8.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.8.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.80.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.80.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.80.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.81.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.81.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.81.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.82.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.82.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.82.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.83.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.83.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.83.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.84.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.84.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.84.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.85.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.85.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.85.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.86.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.86.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.86.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.87.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.87.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.87.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.88.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.88.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.88.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.89.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.89.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.89.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.9.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.9.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.9.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.90.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.90.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.90.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.91.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.91.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.91.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.92.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.92.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.92.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.93.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.93.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.93.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.94.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.94.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.94.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.95.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.95.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.95.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.96.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.96.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.96.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.97.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.97.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.97.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.98.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.98.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.98.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.99.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.99.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.experts.99.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.gate.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.0.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.0.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.0.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.1.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.1.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.1.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.10.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.10.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.10.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.100.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.100.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.100.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.101.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.101.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.101.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.102.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.102.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.102.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.103.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.103.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.103.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.104.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.104.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.104.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.105.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.105.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.105.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.106.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.106.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.106.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.107.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.107.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.107.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.108.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.108.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.108.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.109.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.109.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.109.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.11.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.11.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.11.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.110.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.110.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.110.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.111.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.111.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.111.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.112.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.112.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.112.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.113.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.113.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.113.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.114.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.114.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.114.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.115.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.115.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.115.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.116.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.116.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.116.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.117.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.117.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.117.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.118.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.118.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.118.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.119.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.119.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.119.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.12.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.12.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.12.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.120.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.120.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.120.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.121.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.121.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.121.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.122.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.122.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.122.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.123.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.123.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.123.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.124.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.124.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.124.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.125.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.125.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.125.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.126.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.126.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.126.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.127.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.127.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.127.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.128.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.128.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.128.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.129.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.129.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.129.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.13.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.13.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.13.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.130.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.130.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.130.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.131.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.131.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.131.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.132.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.132.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.132.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.133.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.133.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.133.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.134.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.134.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.134.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.135.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.135.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.135.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.136.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.136.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.136.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.137.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.137.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.137.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.138.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.138.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.138.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.139.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.139.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.139.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.14.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.14.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.14.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.140.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.140.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.140.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.141.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.141.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.141.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.142.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.142.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.142.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.143.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.143.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.143.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.144.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.144.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.144.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.145.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.145.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.145.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.146.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.146.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.146.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.147.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.147.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.147.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.148.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.148.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.148.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.149.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.149.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.149.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.15.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.15.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.15.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.150.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.150.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.150.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.151.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.151.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.151.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.152.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.152.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.152.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.153.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.153.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.153.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.154.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.154.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.154.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.155.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.155.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.155.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.156.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.156.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.156.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.157.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.157.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.157.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.158.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.158.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.158.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.159.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.159.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.159.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.16.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.16.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.16.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.160.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.160.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.160.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.161.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.161.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.161.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.162.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.162.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.162.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.163.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.163.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.163.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.164.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.164.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.164.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.165.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.165.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.165.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.166.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.166.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.166.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.167.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.167.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.167.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.168.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.168.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.168.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.169.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.169.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.169.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.17.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.17.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.17.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.170.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.170.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.170.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.171.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.171.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.171.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.172.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.172.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.172.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.173.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.173.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.173.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.174.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.174.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.174.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.175.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.175.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.175.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.176.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.176.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.176.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.177.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.177.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.177.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.178.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.178.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.178.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.179.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.179.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.179.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.18.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.18.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.18.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.180.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.180.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.180.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.181.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.181.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.181.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.182.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.182.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.182.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.183.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.183.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.183.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.184.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.184.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.184.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.185.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.185.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.185.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.186.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.186.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.186.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.187.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.187.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.187.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.188.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.188.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.188.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.189.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.189.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.189.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.19.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.19.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.19.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.190.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.190.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.190.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.191.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.191.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.191.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.192.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.192.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.192.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.193.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.193.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.193.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.194.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.194.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.194.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.195.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.195.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.195.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.196.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.196.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.196.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.197.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.197.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.197.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.198.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.198.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.198.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.199.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.199.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.199.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.2.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.2.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.2.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.20.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.20.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.20.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.200.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.200.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.200.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.201.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.201.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.201.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.202.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.202.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.202.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.203.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.203.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.203.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.204.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.204.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.204.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.205.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.205.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.205.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.206.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.206.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.206.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.207.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.207.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.207.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.208.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.208.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.208.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.209.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.209.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.209.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.21.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.21.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.21.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.210.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.210.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.210.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.211.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.211.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.211.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.212.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.212.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.212.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.213.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.213.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.213.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.214.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.214.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.214.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.215.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.215.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.215.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.216.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.216.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.216.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.217.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.217.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.217.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.218.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.218.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.218.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.219.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.219.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.219.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.22.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.22.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.22.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.220.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.220.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.220.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.221.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.221.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.221.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.222.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.222.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.222.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.223.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.223.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.223.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.224.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.224.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.224.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.225.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.225.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.225.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.226.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.226.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.226.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.227.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.227.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.227.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.228.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.228.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.228.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.229.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.229.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.229.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.23.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.23.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.23.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.230.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.230.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.230.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.231.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.231.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.231.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.232.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.232.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.232.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.233.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.233.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.233.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.234.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.234.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.234.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.235.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.235.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.235.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.236.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.236.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.236.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.237.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.237.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.237.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.238.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.238.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.238.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.239.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.239.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.239.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.24.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.24.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.24.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.240.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.240.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.240.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.241.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.241.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.241.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.242.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.242.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.242.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.243.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.243.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.243.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.244.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.244.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.244.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.245.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.245.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.245.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.246.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.246.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.246.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.247.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.247.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.247.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.248.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.248.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.248.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.249.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.249.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.249.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.25.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.25.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.25.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.250.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.250.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.250.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.251.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.251.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.251.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.252.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.252.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.252.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.253.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.253.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.253.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.254.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.254.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.254.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.255.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.255.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.255.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.26.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.26.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.26.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.27.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.27.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.27.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.28.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.28.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.28.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.29.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.29.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.29.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.3.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.3.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.3.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.30.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.30.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.30.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.31.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.31.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.31.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.32.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.32.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.32.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.33.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.33.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.33.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.34.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.34.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.34.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.35.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.35.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.35.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.36.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.36.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.36.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.37.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.37.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.37.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.38.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.38.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.38.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.39.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.39.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.39.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.4.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.4.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.4.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.40.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.40.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.40.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.41.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.41.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.41.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.42.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.42.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.42.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.43.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.43.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.43.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.44.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.44.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.44.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.45.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.45.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.45.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.46.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.46.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.46.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.47.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.47.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.47.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.48.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.48.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.48.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.49.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.49.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.49.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.5.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.5.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.5.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.50.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.50.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.50.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.51.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.51.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.51.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.52.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.52.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.52.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.53.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.53.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.53.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.54.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.54.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.54.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.55.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.55.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.55.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.56.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.56.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.56.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.57.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.57.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.57.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.58.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.58.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.58.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.59.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.59.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.59.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.6.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.6.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.6.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.60.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.60.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.60.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.61.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.61.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.61.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.62.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.62.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.62.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.63.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.63.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.63.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.64.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.64.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.64.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.65.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.65.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.65.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.66.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.66.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.66.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.67.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.67.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.67.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.68.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.68.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.68.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.69.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.69.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.69.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.7.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.7.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.7.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.70.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.70.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.70.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.71.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.71.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.71.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.72.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.72.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.72.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.73.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.73.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.73.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.74.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.74.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.74.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.75.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.75.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.75.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.76.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.76.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.76.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.77.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.77.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.77.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.78.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.78.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.78.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.79.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.79.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.79.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.8.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.8.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.8.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.80.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.80.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.80.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.81.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.81.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.81.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.82.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.82.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.82.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.83.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.83.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.83.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.84.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.84.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.84.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.85.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.85.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.85.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.86.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.86.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.86.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.87.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.87.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.87.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.88.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.88.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.88.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.89.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.89.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.89.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.9.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.9.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.9.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.90.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.90.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.90.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.91.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.91.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.91.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.92.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.92.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.92.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.93.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.93.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.93.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.94.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.94.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.94.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.95.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.95.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.95.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.96.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.96.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.96.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.97.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.97.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.97.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.98.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.98.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.98.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.99.down_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.99.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.experts.99.up_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.mlp.gate.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00006-of-00033.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.A_log": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.dt_bias": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.norm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.0.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.0.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.0.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.1.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.1.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.1.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.10.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.10.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.10.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.100.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.100.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.100.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.101.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.101.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.101.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.102.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.102.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.102.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.103.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.103.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.103.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.104.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.104.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.104.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.105.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.105.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.105.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.106.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.106.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.106.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.107.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.107.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.107.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.108.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.108.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.108.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.109.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.109.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.109.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.11.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.11.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.11.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.110.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.110.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.110.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.111.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.111.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.111.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.112.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.112.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.112.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.113.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.113.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.113.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.114.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.114.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.114.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.115.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.115.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.115.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.116.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.116.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.116.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.117.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.117.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.117.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.118.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.118.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.118.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.119.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.119.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.119.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.12.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.12.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.12.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.120.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.120.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.120.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.121.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.121.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.121.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.122.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.122.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.122.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.123.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.123.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.123.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.124.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.124.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.124.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.125.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.125.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.125.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.126.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.126.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.126.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.127.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.127.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.127.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.128.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.128.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.128.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.129.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.129.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.129.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.13.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.13.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.13.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.130.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.130.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.130.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.131.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.131.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.131.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.132.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.132.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.132.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.133.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.133.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.133.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.134.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.134.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.134.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.135.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.135.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.135.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.136.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.136.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.136.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.137.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.137.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.137.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.138.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.138.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.138.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.139.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.139.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.139.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.14.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.14.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.14.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.140.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.140.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.140.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.141.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.141.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.141.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.142.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.142.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.142.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.143.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.143.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.143.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.144.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.144.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.144.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.145.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.145.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.145.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.146.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.146.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.146.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.147.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.147.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.147.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.148.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.148.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.148.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.149.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.149.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.149.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.15.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.15.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.15.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.150.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.150.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.150.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.151.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.151.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.151.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.152.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.152.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.152.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.153.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.153.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.153.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.154.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.154.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.154.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.155.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.155.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.155.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.156.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.156.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.156.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.157.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.157.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.157.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.158.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.158.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.158.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.159.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.159.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.159.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.16.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.16.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.16.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.160.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.160.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.160.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.161.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.161.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.161.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.162.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.162.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.162.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.163.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.163.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.163.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.164.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.164.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.164.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.165.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.165.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.165.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.166.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.166.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.166.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.167.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.167.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.167.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.168.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.168.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.168.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.169.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.169.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.169.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.17.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.17.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.17.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.170.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.170.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.170.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.171.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.171.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.171.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.172.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.172.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.172.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.173.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.173.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.173.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.174.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.174.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.174.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.175.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.175.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.175.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.176.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.176.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.176.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.177.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.177.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.177.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.178.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.178.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.178.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.179.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.179.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.179.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.18.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.18.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.18.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.180.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.180.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.180.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.181.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.181.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.181.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.182.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.182.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.182.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.183.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.183.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.183.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.184.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.184.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.184.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.185.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.185.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.185.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.186.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.186.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.186.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.187.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.187.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.187.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.188.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.188.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.188.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.189.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.189.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.189.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.19.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.19.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.19.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.190.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.190.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.190.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.191.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.191.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.191.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.192.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.192.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.192.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.193.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.193.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.193.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.194.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.194.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.194.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.195.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.195.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.195.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.196.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.196.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.196.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.197.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.197.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.197.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.198.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.198.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.198.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.199.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.199.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.199.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.2.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.2.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.2.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.20.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.20.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.20.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.200.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.200.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.200.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.201.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.201.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.201.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.202.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.202.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.202.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.203.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.203.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.203.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.204.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.204.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.204.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.205.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.205.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.205.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.206.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.206.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.206.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.207.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.207.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.207.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.208.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.208.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.208.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.209.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.209.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.209.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.21.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.21.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.21.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.210.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.210.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.210.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.211.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.211.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.211.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.212.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.212.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.212.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.213.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.213.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.213.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.214.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.214.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.214.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.215.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.215.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.215.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.216.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.216.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.216.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.217.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.217.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.217.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.218.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.218.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.218.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.219.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.219.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.219.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.22.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.22.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.22.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.220.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.220.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.220.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.221.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.221.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.221.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.222.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.222.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.222.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.223.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.223.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.223.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.224.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.224.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.224.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.225.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.225.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.225.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.226.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.226.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.226.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.227.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.227.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.227.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.228.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.228.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.228.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.229.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.229.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.229.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.23.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.23.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.23.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.230.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.230.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.230.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.231.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.231.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.231.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.232.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.232.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.232.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.233.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.233.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.233.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.234.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.234.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.234.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.235.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.235.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.235.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.236.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.236.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.236.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.237.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.237.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.237.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.238.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.238.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.238.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.239.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.239.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.239.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.24.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.24.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.24.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.240.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.240.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.240.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.241.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.241.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.241.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.242.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.242.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.242.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.243.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.243.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.243.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.244.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.244.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.244.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.245.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.245.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.245.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.246.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.246.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.246.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.247.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.247.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.247.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.248.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.248.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.248.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.249.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.249.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.249.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.25.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.25.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.25.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.250.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.250.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.250.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.251.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.251.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.251.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.252.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.252.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.252.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.253.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.253.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.253.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.254.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.254.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.254.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.255.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.255.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.255.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.26.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.26.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.26.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.27.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.27.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.27.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.28.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.28.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.28.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.29.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.29.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.29.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.3.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.3.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.3.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.30.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.30.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.30.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.31.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.31.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.31.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.32.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.32.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.32.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.33.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.33.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.33.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.34.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.34.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.34.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.35.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.35.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.35.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.36.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.36.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.36.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.37.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.37.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.37.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.38.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.38.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.38.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.39.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.39.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.39.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.4.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.4.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.4.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.40.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.40.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.40.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.41.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.41.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.41.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.42.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.42.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.42.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.43.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.43.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.43.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.44.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.44.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.44.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.45.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.45.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.45.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.46.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.46.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.46.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.47.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.47.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.47.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.48.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.48.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.48.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.49.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.49.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.49.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.5.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.5.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.5.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.50.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.50.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.50.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.51.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.51.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.51.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.52.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.52.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.52.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.53.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.53.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.53.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.54.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.54.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.54.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.55.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.55.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.55.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.56.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.56.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.56.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.57.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.57.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.57.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.58.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.58.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.58.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.59.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.59.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.59.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.6.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.6.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.6.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.60.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.60.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.60.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.61.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.61.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.61.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.62.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.62.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.62.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.63.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.63.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.63.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.64.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.64.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.64.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.65.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.65.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.65.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.66.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.66.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.66.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.67.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.67.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.67.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.68.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.68.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.68.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.69.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.69.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.69.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.7.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.7.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.7.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.70.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.70.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.70.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.71.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.71.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.71.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.72.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.72.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.72.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.73.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.73.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.73.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.74.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.74.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.74.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.75.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.75.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.75.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.76.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.76.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.76.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.77.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.77.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.77.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.78.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.78.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.78.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.79.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.79.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.79.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.8.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.8.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.8.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.80.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.80.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.80.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.81.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.81.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.81.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.82.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.82.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.82.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.83.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.83.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.83.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.84.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.84.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.84.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.85.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.85.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.85.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.86.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.86.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.86.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.87.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.87.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.87.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.88.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.88.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.88.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.89.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.89.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.89.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.9.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.9.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.9.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.90.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.90.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.90.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.91.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.91.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.91.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.92.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.92.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.92.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.93.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.93.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.93.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.94.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.94.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.94.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.95.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.95.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.95.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.96.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.96.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.96.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.97.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.97.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.97.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.98.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.98.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.98.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.99.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.99.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.experts.99.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.gate.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00008-of-00033.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.A_log": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.dt_bias": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.norm.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.0.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.0.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.0.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.1.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.1.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.1.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.10.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.10.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.10.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.100.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.100.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.100.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.101.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.101.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.101.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.102.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.102.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.102.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.103.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.103.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.103.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.104.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.104.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.104.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.105.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.105.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.105.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.106.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.106.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.106.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.107.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.107.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.107.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.108.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.108.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.108.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.109.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.109.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.109.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.11.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.11.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.11.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.110.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.110.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.110.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.111.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.111.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.111.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.112.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.112.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.112.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.113.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.113.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.113.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.114.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.114.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.114.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.115.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.115.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.115.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.116.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.116.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.116.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.117.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.117.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.117.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.118.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.118.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.118.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.119.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.119.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.119.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.12.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.12.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.12.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.120.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.120.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.120.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.121.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.121.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.121.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.122.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.122.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.122.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.123.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.123.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.123.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.124.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.124.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.124.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.125.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.125.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.125.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.126.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.126.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.126.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.127.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.127.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.127.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.128.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.128.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.128.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.129.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.129.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.129.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.13.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.13.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.13.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.130.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.130.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.130.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.131.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.131.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.131.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.132.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.132.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.132.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.133.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.133.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.133.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.134.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.134.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.134.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.135.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.135.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.135.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.136.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.136.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.136.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.137.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.137.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.137.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.138.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.138.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.138.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.139.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.139.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.139.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.14.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.14.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.14.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.140.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.140.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.140.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.141.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.141.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.141.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.142.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.142.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.142.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.143.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.143.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.143.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.144.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.144.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.144.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.145.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.145.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.145.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.146.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.146.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.146.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.147.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.147.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.147.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.148.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.148.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.148.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.149.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.149.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.149.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.15.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.15.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.15.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.150.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.150.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.150.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.151.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.151.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.151.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.152.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.152.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.152.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.153.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.153.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.153.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.154.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.154.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.154.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.155.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.155.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.155.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.156.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.156.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.156.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.157.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.157.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.157.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.158.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.158.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.158.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.159.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.159.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.159.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.16.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.16.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.16.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.160.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.160.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.160.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.161.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.161.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.161.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.162.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.162.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.162.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.163.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.163.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.163.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.164.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.164.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.164.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.165.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.165.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.165.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.166.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.166.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.166.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.167.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.167.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.167.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.168.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.168.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.168.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.169.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.169.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.169.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.17.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.17.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.17.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.170.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.170.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.170.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.171.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.171.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.171.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.172.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.172.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.172.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.173.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.173.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.173.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.174.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.174.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.174.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.175.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.175.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.175.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.176.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.176.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.176.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.177.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.177.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.177.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.178.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.178.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.178.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.179.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.179.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.179.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.18.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.18.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.18.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.180.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.180.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.180.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.181.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.181.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.181.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.182.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.182.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.182.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.183.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.183.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.183.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.184.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.184.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.184.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.185.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.185.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.185.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.186.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.186.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.186.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.187.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.187.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.187.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.188.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.188.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.188.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.189.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.189.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.189.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.19.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.19.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.19.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.190.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.190.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.190.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.191.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.191.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.191.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.192.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.192.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.192.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.193.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.193.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.193.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.194.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.194.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.194.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.195.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.195.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.195.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.196.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.196.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.196.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.197.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.197.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.197.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.198.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.198.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.198.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.199.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.199.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.199.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.2.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.2.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.2.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.20.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.20.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.20.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.200.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.200.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.200.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.201.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.201.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.201.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.202.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.202.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.202.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.203.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.203.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.203.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.204.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.204.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.204.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.205.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.205.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.205.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.206.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.206.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.206.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.207.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.207.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.207.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.208.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.208.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.208.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.209.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.209.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.209.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.21.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.21.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.21.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.210.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.210.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.210.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.211.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.211.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.211.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.212.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.212.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.212.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.213.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.213.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.213.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.214.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.214.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.214.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.215.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.215.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.215.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.216.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.216.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.216.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.217.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.217.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.217.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.218.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.218.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.218.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.219.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.219.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.219.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.22.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.22.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.22.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.220.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.220.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.220.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.221.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.221.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.221.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.222.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.222.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.222.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.223.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.223.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.223.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.224.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.224.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.224.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.225.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.225.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.225.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.226.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.226.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.226.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.227.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.227.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.227.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.228.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.228.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.228.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.229.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.229.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.229.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.23.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.23.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.23.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.230.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.230.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.230.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.231.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.231.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.231.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.232.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.232.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.232.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.233.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.233.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.233.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.234.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.234.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.234.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.235.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.235.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.235.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.236.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.236.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.236.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.237.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.237.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.237.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.238.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.238.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.238.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.239.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.239.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.239.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.24.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.24.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.24.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.240.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.240.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.240.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.241.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.241.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.241.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.242.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.242.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.242.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.243.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.243.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.243.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.244.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.244.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.244.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.245.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.245.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.245.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.246.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.246.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.246.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.247.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.247.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.247.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.248.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.248.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.248.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.249.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.249.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.249.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.25.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.25.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.25.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.250.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.250.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.250.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.251.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.251.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.251.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.252.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.252.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.252.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.253.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.253.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.253.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.254.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.254.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.254.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.255.down_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.255.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.255.up_proj.weight": "model-00010-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.26.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.26.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.26.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.27.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.27.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.27.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.28.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.28.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.28.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.29.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.29.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.29.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.3.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.3.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.3.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.30.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.30.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.30.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.31.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.31.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.31.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.32.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.32.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.32.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.33.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.33.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.33.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.34.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.34.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.34.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.35.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.35.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.35.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.36.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.36.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.36.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.37.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.37.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.37.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.38.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.38.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.38.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.39.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.39.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.39.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.4.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.4.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.4.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.40.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.40.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.40.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.41.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.41.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.41.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.42.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.42.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.42.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.43.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.43.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.43.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.44.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.44.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.44.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.45.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.45.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.45.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.46.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.46.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.46.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.47.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.47.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.47.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.48.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.48.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.48.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.49.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.49.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.49.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.5.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.5.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.5.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.50.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.50.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.50.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.51.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.51.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.51.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.52.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.52.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.52.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.53.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.53.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.53.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.54.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.54.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.54.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.55.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.55.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.55.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.56.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.56.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.56.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.57.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.57.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.57.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.58.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.58.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.58.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.59.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.59.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.59.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.6.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.6.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.6.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.60.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.60.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.60.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.61.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.61.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.61.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.62.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.62.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.62.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.63.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.63.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.63.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.64.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.64.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.64.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.65.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.65.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.65.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.66.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.66.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.66.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.67.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.67.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.67.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.68.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.68.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.68.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.69.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.69.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.69.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.7.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.7.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.7.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.70.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.70.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.70.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.71.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.71.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.71.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.72.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.72.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.72.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.73.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.73.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.73.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.74.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.74.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.74.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.75.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.75.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.75.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.76.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.76.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.76.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.77.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.77.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.77.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.78.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.78.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.78.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.79.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.79.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.79.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.8.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.8.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.8.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.80.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.80.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.80.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.81.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.81.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.81.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.82.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.82.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.82.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.83.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.83.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.83.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.84.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.84.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.84.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.85.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.85.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.85.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.86.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.86.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.86.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.87.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.87.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.87.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.88.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.88.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.88.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.89.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.89.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.89.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.9.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.9.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.9.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.90.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.90.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.90.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.91.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.91.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.91.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.92.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.92.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.92.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.93.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.93.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.93.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.94.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.94.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.94.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.95.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.95.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.95.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.96.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.96.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.96.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.97.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.97.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.97.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.98.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.98.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.98.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.99.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.99.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.experts.99.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.gate.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00009-of-00033.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", + "model.language_model.norm.weight": "model-00033-of-00033.safetensors" } } diff --git a/qwen_vllm_wrapper_repair_v3.json b/qwen_vllm_wrapper_repair_v3.json new file mode 100644 index 0000000000000000000000000000000000000000..9c648fee8e15f9f600677133d8c9bfcbffd0ae64 --- /dev/null +++ b/qwen_vllm_wrapper_repair_v3.json @@ -0,0 +1,44 @@ +{ + "config": { + "architectures": [ + "Qwen3_5MoeForConditionalGeneration" + ], + "dtype": "bfloat16", + "has_text_config": true, + "has_vision_config": true, + "model_type": "qwen3_5_moe", + "removed_quantization": [], + "replaced_with_wrapper_config": true, + "source_architectures": [ + "Qwen3_5MoeForConditionalGeneration" + ], + "source_layout": "wrapper", + "source_model_type": "qwen3_5_moe", + "updated": true + }, + "expert_layout": "per_expert", + "metadata": { + "shards": 33, + "total_parameters": 34660610688, + "total_size": 69321221376 + }, + "model_id": "agents-a1-4bit", + "model_path": "/Users/mike/Desktop/EXO/mlx-to-vllm-export/outputs/agents-a1-4bit-text-dequant-bf16", + "source_layout": "wrapper", + "stats": { + "down_proj_renamed": 0, + "fused_per_expert_tensors_written": 0, + "fused_tensors_removed": 0, + "gate_up_proj_fused": 0, + "input_shards_deleted_after_streaming": 14, + "input_tensors": 733, + "language_model_lm_head_rewritten": 1, + "language_model_model_prefix_rewritten": 732, + "language_model_prefix_rewritten": 0, + "model_language_model_prefix_rewritten": 0, + "passthrough_tensors": 613, + "standalone_model_prefix_rewritten": 0, + "switch_mlp_per_expert_tensors_written": 30720, + "switch_tensors_removed": 120 + } +}