diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..ecb8be2c9e22f947354626254b7a78ee3527a582 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,8 @@ +{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user +' + message['content'] + '<|im_end|> +'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant +' + message['content'] + '<|im_end|> +' }}{% else %}{{ '<|im_start|>system +' + message['content'] + '<|im_end|> +' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant +' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5402cdf7b499655aad576dde6ed2b0d45f83dda4 --- /dev/null +++ b/config.json @@ -0,0 +1,104 @@ +{ + "architectures": [ + "Glm4MoeLiteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 0, + "torch_dtype": "bfloat16", + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "first_k_dense_replace": 1, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 10240, + "kv_lora_rank": 512, + "max_position_embeddings": 202752, + "mlp_layer_types": [ + "dense", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse" + ], + "model_type": "glm4_moe_lite", + "moe_intermediate_size": 1536, + "n_group": 1, + "n_routed_experts": 64, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 20, + "num_experts_per_tok": 4, + "num_hidden_layers": 47, + "num_key_value_heads": 20, + "num_nextn_predict_layers": 1, + "pad_token_id": 154821, + "partial_rotary_factor": 1.0, + "pretraining_tp": 1, + "q_lora_rank": 768, + "qk_head_dim": 256, + "qk_nope_head_dim": 192, + "qk_rope_head_dim": 64, + "rms_norm_eps": 1e-05, + "rope_interleave": true, + "rope_parameters": { + "partial_rotary_factor": 1.0, + "rope_theta": 1000000, + "rope_type": "default" + }, + "routed_scaling_factor": 1.8, + "scoring_func": "sigmoid", + "tie_word_embeddings": false, + "topk_group": 1, + "topk_method": "noaux_tc", + "unsloth_fixed": true, + "use_cache": true, + "v_head_dim": 256, + "vocab_size": 154880 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..34ee35bf3c3acce6432ee6db632c960c6fb2e89a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,16 @@ +{ + "_from_model_config": true, + "do_sample": true, + "eos_token_id": [ + 154820, + 154820, + 154820, + 154827, + 154829 + ], + "max_length": 202752, + "pad_token_id": 154821, + "temperature": 1.0, + "top_p": 0.95, + "transformers_version": "5.5.0" +} diff --git a/model-00001-of-00048.safetensors b/model-00001-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a156c89b6658e7f8c9cb5108ec7c87e3a2a16f97 --- /dev/null +++ b/model-00001-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1872d01fbdc5a5aaaaa30a12a2f9d619c063a6163b59f46f98605efab712d1 +size 1438134344 diff --git a/model-00002-of-00048.safetensors b/model-00002-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7194a9fad0c7e3bf643d9c82489579b92164f578 --- /dev/null +++ b/model-00002-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfc5be4a1f1b86a99a438015d23cacf79f484e96564d1e4c05c1b1592ab0d19 +size 1270648128 diff --git a/model-00003-of-00048.safetensors b/model-00003-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c35ae04ed72cb9e21064d65a3e30ff8d86664e25 --- /dev/null +++ b/model-00003-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2bc05b9cf143ef692145284c19c342abf08e2f23fc3607e1d84e504e2c9894 +size 1270648128 diff --git a/model-00004-of-00048.safetensors b/model-00004-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1da1fc79eea00c0b2e4d54f03ec78ee240f62c2 --- /dev/null +++ b/model-00004-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d99c86f5207eba6ee51c777f62bffdddc1aefda419edb4f8be5164884bb77bf +size 1270648128 diff --git a/model-00005-of-00048.safetensors b/model-00005-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd2e1d235ac0e1a162867a82f4e7f5787e50ee0b --- /dev/null +++ b/model-00005-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f304058e474e1e6ed4b235f699f604178ea448a48279182548d48fcf23a4cf6 +size 1270648128 diff --git a/model-00006-of-00048.safetensors b/model-00006-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b722a4940305387c94e54bc52a043d89c8cb15c3 --- /dev/null +++ b/model-00006-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd1a14c6807ca88aeafbf67c9e9562493ead3f93b4e2c8855913be7d9fb7800 +size 1270648128 diff --git a/model-00007-of-00048.safetensors b/model-00007-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05fc1676e7c773f6d307cb53a3bba3482e1aa64d --- /dev/null +++ b/model-00007-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13651b52e42e8cdeb2b92c9168f4f425c69c1b8b2aaebf2d837915eebff1db70 +size 1270648128 diff --git a/model-00008-of-00048.safetensors b/model-00008-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..838b183e67f2faf345aec32accffac4f2d90bf20 --- /dev/null +++ b/model-00008-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a49a60befc035244b00bdadf50c6e3e15ae55873bf8331a793453aa3ef48a37 +size 1270648128 diff --git a/model-00009-of-00048.safetensors b/model-00009-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbf5c0347803ab2d4c8e49cc27a8b86610137f6f --- /dev/null +++ b/model-00009-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8bdec6673a1e84962331cc384189234352fd9dddedc31044ebb5629bf00ff92 +size 1270648128 diff --git a/model-00010-of-00048.safetensors b/model-00010-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78e0a030a4c49687593250c7f1285163a00fe26d --- /dev/null +++ b/model-00010-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87216ff869f5abdeabee181201248d86d2dad14448e4e06eabd75e9415fa217 +size 1270648128 diff --git a/model-00011-of-00048.safetensors b/model-00011-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..84e3e4db176b65144d0f5a2bebd2a70c3dba9ed6 --- /dev/null +++ b/model-00011-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c0bc6d62f940412c541be04b35406e12caffa5c5896a454be63099df37e6f7 +size 1270648328 diff --git a/model-00012-of-00048.safetensors b/model-00012-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..717d9b45b6457e1f09b73dcfd85a79b66d646889 --- /dev/null +++ b/model-00012-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a983bb7939dcc56ea9c6216df0a924f5f077d0b1bad7b184285bb7ed5e92437 +size 1270648328 diff --git a/model-00013-of-00048.safetensors b/model-00013-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42d1bed2178f4fee7069e4de065955d05bd409ca --- /dev/null +++ b/model-00013-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:462e188c6b5a46a89bcb74d36663d713d04b1f081602ac56d6ce5701eb620542 +size 1270648328 diff --git a/model-00014-of-00048.safetensors b/model-00014-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90207a142df3af7d01dbbe14d59d479ffad2895d --- /dev/null +++ b/model-00014-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7449a753f0e6922571614894bff0a0daf1a3824b2bb2e4111aabc4dce80df124 +size 1270648328 diff --git a/model-00015-of-00048.safetensors b/model-00015-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86523bf5923e4a4f420d4d6a1a6faf22708163af --- /dev/null +++ b/model-00015-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ecf77bb9410bbedd5e20d2730a4e6558d6de9a4b99e60f26769eb147b79a76 +size 1270648328 diff --git a/model-00016-of-00048.safetensors b/model-00016-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acdaa4cf39306fa807f4a4e4ee474a8bec8ef64d --- /dev/null +++ b/model-00016-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:430c7a669b1e3905767c43b2191306a8f214916e5c6e9a936e927ac428613f59 +size 1270648328 diff --git a/model-00017-of-00048.safetensors b/model-00017-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d2b809d85c3f4f15ffdab23147f73492c65e4a4 --- /dev/null +++ b/model-00017-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d0c0f80dac2cbd07eb851efb0869e2e2f2281add87875cce0b7d525b0f2b32 +size 1270648328 diff --git a/model-00018-of-00048.safetensors b/model-00018-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a0cd1cf8baa5a30394cf7da1240a85cc244d4e0 --- /dev/null +++ b/model-00018-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3ca1d2d09fecec4d7f9a05d22aecba97e8b3a35824804321f65fc1fddb0822 +size 1270648328 diff --git a/model-00019-of-00048.safetensors b/model-00019-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77d0b305052f80917df4b85c27b31a30c2260ddb --- /dev/null +++ b/model-00019-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6179f3c51c96f3974a1a96e35bf2e9bb7b874c7d6dff53af027c1f9f604dba1c +size 1270648328 diff --git a/model-00020-of-00048.safetensors b/model-00020-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85c4945bea38d8f2f93b3a3ecafd809d1e19be0f --- /dev/null +++ b/model-00020-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a5f5903d66cf66d9fb30a0d74b504c7d4c0c21bcbcb4b3115193ac2405b5d4 +size 1270648328 diff --git a/model-00021-of-00048.safetensors b/model-00021-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e1c67bf2ea12f2c89a30e7654fca3f97a5d43a3 --- /dev/null +++ b/model-00021-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac91eeb1310b29a4440426d29870005f09ff46f9988807bdff31b64bfa3e283 +size 1270648328 diff --git a/model-00022-of-00048.safetensors b/model-00022-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..612af434acc794d2cb2a97013e3e69b76c8a2e00 --- /dev/null +++ b/model-00022-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4077ecb56c14737f544035c3c2fa8fda9c37621d6dd7945cc3a96a865010c97 +size 1270648328 diff --git a/model-00023-of-00048.safetensors b/model-00023-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2dab8d4ff09ccc95a9b9ccf27c9376cc7fde4876 --- /dev/null +++ b/model-00023-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881cbffa6f1eefd586763d43e969d0fbb3dede4128bdbed5cc890fb86ffc5c2a +size 1270648328 diff --git a/model-00024-of-00048.safetensors b/model-00024-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f66ed6f16176108045a67530eb6c9acd81a39e35 --- /dev/null +++ b/model-00024-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bff9db18c6373255605cc68fcf10eaadfc0c0c98d49bd3b0726774d66e72cf8 +size 1270648328 diff --git a/model-00025-of-00048.safetensors b/model-00025-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc4669f35be15a9cc6b4ddcf69854d7cb99537b4 --- /dev/null +++ b/model-00025-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e277d21f31f64e96bbbbd95b0b138cd303369edd1f49cc032d976c680f6e4ce9 +size 1270648328 diff --git a/model-00026-of-00048.safetensors b/model-00026-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6de432e5f56945cd0f628c7ed3ad97e68f7d331 --- /dev/null +++ b/model-00026-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83ed9a62005b8ee2e47d70697f9d275b539320477d4e99ea3c43e6149dfbf55 +size 1270648328 diff --git a/model-00027-of-00048.safetensors b/model-00027-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4c9cdee60f9eb00a68490e84c0f991b7c95decd --- /dev/null +++ b/model-00027-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aab9685d54ee011916c6f419f1f55ecdb580e90acadd8601eed3eac174bc108 +size 1270648328 diff --git a/model-00028-of-00048.safetensors b/model-00028-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..656f382a74d2b69ec197fc113aaa90f3de6526d4 --- /dev/null +++ b/model-00028-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c1cabc0ceb66daed0985173942faf76b1f6d93154f0d403578cbca4b165e47 +size 1270648328 diff --git a/model-00029-of-00048.safetensors b/model-00029-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db97e2525a5504bc23481a71aabd8f70435d11cd --- /dev/null +++ b/model-00029-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d66cf8b4673020c5842c09467fd49dce90b705350accb2a8debd37c97795c9a +size 1270648328 diff --git a/model-00030-of-00048.safetensors b/model-00030-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a64cd02250d1001242303d6f0faf77b0f444693 --- /dev/null +++ b/model-00030-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7784b29f1353efe15ac384dfec88635458b6fc2f7758f47da6509bf29067ee +size 1270648328 diff --git a/model-00031-of-00048.safetensors b/model-00031-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac1149bbff804f0338f470fa5bdb107fb5cea67b --- /dev/null +++ b/model-00031-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6206fbe24892791173d154fb52e0508215d61a76a9b97e27f15986f5d641d7 +size 1270648328 diff --git a/model-00032-of-00048.safetensors b/model-00032-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..158ce3de955e1f1f4a41cdbce7a26e0fc3851ab4 --- /dev/null +++ b/model-00032-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5cdf5d06c27a73beb0fb1806d69d74b8556c9dedc2432197340e6a2519dce62 +size 1270648328 diff --git a/model-00033-of-00048.safetensors b/model-00033-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a562afac929f6f12cb50b9abd39aa712e71c2674 --- /dev/null +++ b/model-00033-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:957883b9190fe2cec1893d7940d83c36f81527c9c772d281067ada0b9b6120a1 +size 1270648328 diff --git a/model-00034-of-00048.safetensors b/model-00034-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d146a088fba3bf50e8c79c4fd5148ab110611022 --- /dev/null +++ b/model-00034-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b12046e9af2026d692e6da0f24c6a265c3d5833920df4441b41a1f7357bd60c +size 1270648328 diff --git a/model-00035-of-00048.safetensors b/model-00035-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5165e98bde59dc6ac41bf45e5accbaa395388369 --- /dev/null +++ b/model-00035-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f009c1834902b32eb1eaa916827a9de2a10d00b6ea48022cf999f104238c61b +size 1270648328 diff --git a/model-00036-of-00048.safetensors b/model-00036-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55fabd32d11890a720ff05d4c96a7efd3d7783d9 --- /dev/null +++ b/model-00036-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9746a40df79bce40cb8b94da3f987b632e71e68e57483e2d2fbd44104eaad270 +size 1270648328 diff --git a/model-00037-of-00048.safetensors b/model-00037-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..885a78c382ac74061c01f5a7506f619756239aa4 --- /dev/null +++ b/model-00037-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e22d0e0b71e87a7ed7d4d49dd021e54e30c4fe3184fc5933d521a140b3403f9 +size 1270648328 diff --git a/model-00038-of-00048.safetensors b/model-00038-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78f7db09802f28ea803ae9fcae99153a9e5ce5f8 --- /dev/null +++ b/model-00038-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f97b94875c19114ddac00f48a87729c7b62d9b15ba649cedd393e1b8d7fa12 +size 1270648328 diff --git a/model-00039-of-00048.safetensors b/model-00039-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58b459b4547ec8118159b0f9a1b697f8bd2486ca --- /dev/null +++ b/model-00039-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d35bb226684e2c066d6b1b2749f774aed68ce7e8c3bf8859d5a5bc81de4755f +size 1270648328 diff --git a/model-00040-of-00048.safetensors b/model-00040-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..babb161d804a65ee34a9f6ff36ca0935c0954a0b --- /dev/null +++ b/model-00040-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a96046ef78b7fbbb0f167fc0916109ad7631294b3376f8ef3a0c1edaaf10ba1 +size 1270648328 diff --git a/model-00041-of-00048.safetensors b/model-00041-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b7f2a511def7871da0b9390bfa0b4dba7b1b84e --- /dev/null +++ b/model-00041-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e33a69f561739d9ddf6613d392f40690385343f997bda02465118dd805da0cd +size 1270648328 diff --git a/model-00042-of-00048.safetensors b/model-00042-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0280119bfa1b4b27482987abf043ae2cd2fded4b --- /dev/null +++ b/model-00042-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de8c634d96487ef97d3570b303d0b0022a435d8e3900eb53cbccb8080963389 +size 1270648328 diff --git a/model-00043-of-00048.safetensors b/model-00043-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df262c63506eb707965c8acdfc4e79c108549656 --- /dev/null +++ b/model-00043-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec54465f8cfc78d7347e00962939077ce24eec70e9527f3110a6c2d27109700 +size 1270648328 diff --git a/model-00044-of-00048.safetensors b/model-00044-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c68b0f064173b86e5b9117d8bb57543d52cf296 --- /dev/null +++ b/model-00044-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28293fb4059edcb2e1daadb8f5d709633117a55b2f67131cd83cb6aae6e292ed +size 1270648328 diff --git a/model-00045-of-00048.safetensors b/model-00045-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1e4a8282caddd77b25d37c51c088ed8dce9bd7e --- /dev/null +++ b/model-00045-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e462aa7a07b24b90c75e06421bbc90208417ecee8f559acce131da6cf348db9 +size 1270648328 diff --git a/model-00046-of-00048.safetensors b/model-00046-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26b1c8459f52ca049ae30e93092426bc905cffc3 --- /dev/null +++ b/model-00046-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a4b1f7c7d02d5a88408f96b2dc21186f910898f5ff48ed99e9c6a5a74176c7 +size 1270648328 diff --git a/model-00047-of-00048.safetensors b/model-00047-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be46135433daaad4db277bcdd9018d24359e906b --- /dev/null +++ b/model-00047-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45aa44c8f93550c0ee30a86f9e2868c4d86f8e8816ac68585fe0e69013ad97b +size 2539429936 diff --git a/model-00048-of-00048.safetensors b/model-00048-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66dc5fc40d32acc196b9686568f96f35dc95a747 --- /dev/null +++ b/model-00048-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35fff90a30ca808d86dc24f9e3eda119832ab69fb1f88ae4cccfbf0e5ee409a1 +size 1287438264 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..215064e6cfa2a56b41b5ef618d82b802a103cdfc --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,9710 @@ +{ + "metadata": { + "total_size": 31221488576 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.47.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_b_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_b_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_b_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_b_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_b_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_b_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_b_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_b_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_b_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_b_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_b_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_b_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_b_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_b_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_b_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_b_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_b_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_b_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_b_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_b_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_b_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_b_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_b_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_b_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_b_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_b_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_b_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_b_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_b_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_b_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_b_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_b_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_b_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_b_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_b_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_b_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_b_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_b_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_b_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_b_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_b_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_b_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_b_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_b_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_b_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_b_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_b_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_b_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_b_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_b_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_b_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_b_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_b_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_b_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_b_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_b_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_b_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_b_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_b_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_b_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_b_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_b_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_b_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_b_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_b_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_b_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_b_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_b_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_b_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_b_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_b_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_b_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_b_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_b_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_b_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_b_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_b_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_b_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_b_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_b_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_b_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_b_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_b_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_b_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_b_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_b_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_b_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_b_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_b_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_b_proj.weight": "model-00046-of-00048.safetensors", + "lm_head.weight": "model-00047-of-00048.safetensors", + "model.layers.46.input_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_b_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_b_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.47.shared_head.head.weight": "model-00047-of-00048.safetensors", + "model.norm.weight": "model-00047-of-00048.safetensors", + "model.layers.47.eh_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.enorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.hnorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.input_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.gate.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_proj_with_mqa.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_b_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_b_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.shared_head.norm.weight": "model-00048-of-00048.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..72db0afe673754fce70de6e3f7b175197ac7967a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c891b5bacf6670ca67246ac96d0d1e518d7e9d3c588c79b095f82aa49b754b +size 20217439 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..769025b556e87f028047721681994daf0eaf4b40 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,300 @@ +{ + "backend": "tokenizers", + "bos_token": null, + "eos_token": "<|im_end|>", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "[MASK]", + "tokenizer_class": "TokenizersBackend", + "unk_token": null, + "added_tokens_decoder": { + "154820": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154821": { + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154822": { + "content": "[gMASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154823": { + "content": "[sMASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154824": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154825": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154826": { + "content": "<|system|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154827": { + "content": "<|user|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154828": { + "content": "<|assistant|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154829": { + "content": "<|observation|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154830": { + "content": "<|begin_of_image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154831": { + "content": "<|end_of_image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154832": { + "content": "<|begin_of_video|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154833": { + "content": "<|end_of_video|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154834": { + "content": "<|begin_of_audio|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154835": { + "content": "<|end_of_audio|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154836": { + "content": "<|begin_of_transcription|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154837": { + "content": "<|end_of_transcription|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154838": { + "content": "<|code_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154839": { + "content": "<|code_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154840": { + "content": "<|code_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154841": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154842": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154843": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154844": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154845": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154846": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154847": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154848": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154849": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154850": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154851": { + "content": "/nothink", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154852": { + "content": "<|begin_of_box|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154853": { + "content": "<|end_of_box|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154854": { + "content": "<|image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154855": { + "content": "<|video|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + } + }, + "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}" +} \ No newline at end of file