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/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..db1f57018098b3fb19508b063fbb9c11925f19fe --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# prototype-0.4x329 + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [Multi-SLERP](https://goddard.blog/posts/multislerp-wow-what-a-cool-idea) merge method using /workspace/cache/models--deepcogito--cogito-v2-preview-llama-70B/snapshots/1e1d12e8eaebd6084a8dcf45ecdeaa2f4b8879ce as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/cache/models--TheDrummer--Anubis-70B-v1/snapshots/e50d699bf6c21afcf4dbd9a8b4f73511b0366efb +* /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1/snapshots/e50d699bf6c21afcf4dbd9a8b4f73511b0366efb + parameters: + weight: [0.5] + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + parameters: + weight: [0.5] +base_model: /workspace/cache/models--deepcogito--cogito-v2-preview-llama-70B/snapshots/1e1d12e8eaebd6084a8dcf45ecdeaa2f4b8879ce +merge_method: multislerp +tokenizer: + source: base +chat_template: llama3 +parameters: + normalize_weights: false + eps: 1e-9 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..0fcec78aaef89ed38b6a242c7405180036efc138 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set loop_messages = messages %} +{% for message in loop_messages %} +{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %} +{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %} +{{ content }} +{% endfor %} +{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..7478572fe0bca0db1cf4be646934093eb6c74641 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.2", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..830c6d628ae8d5a2fe5b38db72b4cc3a40f21c82 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,18 @@ +models: + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1/snapshots/e50d699bf6c21afcf4dbd9a8b4f73511b0366efb + parameters: + weight: [0.5] + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + parameters: + weight: [0.5] +base_model: /workspace/cache/models--deepcogito--cogito-v2-preview-llama-70B/snapshots/1e1d12e8eaebd6084a8dcf45ecdeaa2f4b8879ce +merge_method: multislerp +tokenizer: + source: base +chat_template: llama3 +parameters: + normalize_weights: false + eps: 1e-9 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 \ No newline at end of file diff --git a/model-00001-of-00063.safetensors b/model-00001-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0f2f2075c36ea067c2ae94299ce3cfa64f91503 --- /dev/null +++ b/model-00001-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df450f7d7af904e8256bfad0042b066a6942ea4ee9533d0847e41032f825896 +size 4362175752 diff --git a/model-00002-of-00063.safetensors b/model-00002-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fe99f12276ff21851b95225d4ac5b05edcf8d7b --- /dev/null +++ b/model-00002-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155e8dd4bda50386d554dd99cd8bee81493aefb7e49cdbc6744d33eedf39efb2 +size 4429251992 diff --git a/model-00003-of-00063.safetensors b/model-00003-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8698a6945ddb858350f07e25c149ca666d9937df --- /dev/null +++ b/model-00003-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1ec20f4a7eaafce6a107b37452ffd37eeed79d539436604072511453a551f9 +size 3154150224 diff --git a/model-00004-of-00063.safetensors b/model-00004-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..076ec218c41809ff37a2c3c597585ca29efb76b1 --- /dev/null +++ b/model-00004-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03ae15dae370db122e091e490a12256c2846e6ba5d6ddb36d068b5aa18a9c284 +size 4236247288 diff --git a/model-00005-of-00063.safetensors b/model-00005-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1d358f4ed60f60f10fbc6891649cfd861cb9404 --- /dev/null +++ b/model-00005-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587fe359a27e0f2255010b107d696b7e920c09fa02093ae0020e877d81197eda +size 4462806536 diff --git a/model-00006-of-00063.safetensors b/model-00006-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f50b1ee33d07835b569ac9f4b5c207adf2afdb9 --- /dev/null +++ b/model-00006-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e85521bf7f7d72396db1ad480d9181930bf7aa5e4b13e82361fd85f7bca9ad +size 2181071464 diff --git a/model-00007-of-00063.safetensors b/model-00007-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b91ee07a14d40a8a452ecf6f5d128c47de6f3b43 --- /dev/null +++ b/model-00007-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81afecb58ae1935c206f6c480165f4c682caee2dc22e6589a72c40d1cf3ae0f +size 4504682872 diff --git a/model-00008-of-00063.safetensors b/model-00008-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da8fbaaa96c7d549fc1ee1cd0b20fccaae8f6965 --- /dev/null +++ b/model-00008-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c1b49a1fb31f575a7bc9c78dc844d75298f0067e3b6a1509acd213b29a9b21d +size 4362208640 diff --git a/model-00009-of-00063.safetensors b/model-00009-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87ae0e78558affa85c8dbf77b1b728724008ade4 --- /dev/null +++ b/model-00009-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbea6b6ce8ccf3e0afa5a82b1cfd76ad3a76ec50e47db654273cda0f6ea85d6e +size 4630578456 diff --git a/model-00010-of-00063.safetensors b/model-00010-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e2770b2e79f2343f40e3ed856f6ff2eba8c3d21 --- /dev/null +++ b/model-00010-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a27a4f35360f0635d954653a1281f17766ce6cc94fd3431b703b480e736d05b +size 4697687552 diff --git a/model-00011-of-00063.safetensors b/model-00011-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb801f82f2dd0735119723c3888e078a37690b79 --- /dev/null +++ b/model-00011-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7538d227c6e0b6c2dbe859541e9a5c890db2cd8f0ed2ca5e42ebcf4b7fad497e +size 4362208640 diff --git a/model-00012-of-00063.safetensors b/model-00012-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4d8334633348305e5f725fd66b4d4b24938c71f --- /dev/null +++ b/model-00012-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab1cf8415bad5e25d857d80780cfe9e06cd92785870fc8d13a7157963f6059c +size 4362142888 diff --git a/model-00013-of-00063.safetensors b/model-00013-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f203540025542f24a066aa5cbbbc9d40a6a40a9 --- /dev/null +++ b/model-00013-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20418420db6217012bd860052de05d11d93cfb757f23eaebb83f59efdb69bd5a +size 4966123128 diff --git a/model-00014-of-00063.safetensors b/model-00014-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd4ff4815462755afcc178bf15164d1bd44c3867 --- /dev/null +++ b/model-00014-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbd233693793fda525781ad22399cfd1819bbbe7f5f2010aa2aad93ed498bbb +size 4362208640 diff --git a/model-00015-of-00063.safetensors b/model-00015-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23968bd570559f660cf2582c7be36a6b5de2ddd1 --- /dev/null +++ b/model-00015-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:693d73d72db36f2db3206c80e1c84c05a3ccdae8ba28d96eccc95eec06e29d19 +size 4362142888 diff --git a/model-00016-of-00063.safetensors b/model-00016-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8ef1f91fa4f86f8e558c1ab8132fec6dc4a5280 --- /dev/null +++ b/model-00016-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f376bb9676e7f340b95a5a7c2620068111fb6f52328be7c45e5d589b2ef42a +size 4966123128 diff --git a/model-00017-of-00063.safetensors b/model-00017-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b69c48bd37c920e9ffb7bf43771c4bc42606f136 --- /dev/null +++ b/model-00017-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f50394df80aab5d2646d1a2e2b487bacbcfa7a1b61816adcb7cacba2a901df0 +size 4362208640 diff --git a/model-00018-of-00063.safetensors b/model-00018-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20d101ba06f93cc86da9dbd215ab9d353fa5d759 --- /dev/null +++ b/model-00018-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d7e767c14e514b3666bfc36a2bf26fd2558a968b8e0d35ac4138790da611f19 +size 4362142888 diff --git a/model-00019-of-00063.safetensors b/model-00019-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62f6ed5f6f8716e773ac865dd1221f970e403965 --- /dev/null +++ b/model-00019-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea1da2fadf94d6e3ed5e0e03f6b33c651ebd8db356bfcd4fa90961d459e2346 +size 4966156000 diff --git a/model-00020-of-00063.safetensors b/model-00020-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2074f964f6653e1a20989563cb65577fb92f0b68 --- /dev/null +++ b/model-00020-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f56fcd8c2a82286682ba2e1230e6e49de3ba90d0766702b82603709edd4c409 +size 4362142888 diff --git a/model-00021-of-00063.safetensors b/model-00021-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29f53914cacd5858b5173afc2215ed100f302ccb --- /dev/null +++ b/model-00021-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d077cd518bec2be8ad87742662890c40f27b5f90fcb081ff5700293adb2fdb0e +size 4395730320 diff --git a/model-00022-of-00063.safetensors b/model-00022-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1586d847d5d14e800f2e72be9f21fc1cfd228f0c --- /dev/null +++ b/model-00022-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a37e7a9e1bb902350b8a7f55425c3e0e80168b10f55e95538159da335f1c07a +size 4932601456 diff --git a/model-00023-of-00063.safetensors b/model-00023-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d60c13280d27b399f2358b3d0ed2426352396868 --- /dev/null +++ b/model-00023-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29929b81894eec197b08fb983260d2acba87db92f1b2d435f45f9bb9e2f3e290 +size 4395697432 diff --git a/model-00024-of-00063.safetensors b/model-00024-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73742b1d93926b99f4839c01ecc29af6748f7279 --- /dev/null +++ b/model-00024-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7483e79523cfad47a1bf32b0ed6a1076e414ac1a3f926332ee444d036279bf1 +size 4395730320 diff --git a/model-00025-of-00063.safetensors b/model-00025-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f03df08bc6cbe193886f0fa46b8d3a280f49badd --- /dev/null +++ b/model-00025-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd938a352a74ed5ef989ceb3e989a66e534f1d95681539809cc9a406f4963469 +size 4630578456 diff --git a/model-00026-of-00063.safetensors b/model-00026-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e699f6f1ece2f91b8ef48bdd11f29a3759ab3392 --- /dev/null +++ b/model-00026-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d4d20dc1c70693c7a2949579185a0354b72db3ace129b25ab6fd81ba4a4014 +size 4664165888 diff --git a/model-00027-of-00063.safetensors b/model-00027-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..795a199c56f0025af6fd3c1aa60390d8145199fd --- /dev/null +++ b/model-00027-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac15da2ab3f920f6d1c0d627d31c32ab08543a4fefa7932d345de1488528a53b +size 4395730320 diff --git a/model-00028-of-00063.safetensors b/model-00028-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..539d6841dcb0c85349faa68550c82ffb6129a580 --- /dev/null +++ b/model-00028-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39a84ff4a8df4049aa8644b5e66740b0f47012d334603f3195ac81d8b430dbe +size 4630578456 diff --git a/model-00029-of-00063.safetensors b/model-00029-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b5f5a6c0161de1e32a91c8f6f1198461aac6727 --- /dev/null +++ b/model-00029-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b4925d11c3d1f7cd1dc823b8b66490a7db2c03a912d5a6392e58f0177f09aed +size 4664165888 diff --git a/model-00030-of-00063.safetensors b/model-00030-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..596bdea3c22fe23ae0e91d9410427c097e3c11a8 --- /dev/null +++ b/model-00030-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083babcd71b100daffcf84eed694b168d6d6a673028f12ccdfff0c999125c7be +size 4395730320 diff --git a/model-00031-of-00063.safetensors b/model-00031-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..83577d08da476fbcf84b1e351985a41b21114375 --- /dev/null +++ b/model-00031-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fae1fcb82ee6803aaacff99f2b6013ec8de2cb6d95fc2e50c521a7d364e1528 +size 4630578456 diff --git a/model-00032-of-00063.safetensors b/model-00032-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98180a9a7f4146a280c7527b5e5a199e1d967115 --- /dev/null +++ b/model-00032-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12577594781a72274c3a56f7a426ff5a09286c64d97e0af1ba2d248f5d10b17 +size 4664165880 diff --git a/model-00033-of-00063.safetensors b/model-00033-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21558eb6c348a652c0c3462b68500a90671bc3a8 --- /dev/null +++ b/model-00033-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4d95672d0f7f841cdf2adb7839ae2727dd9556380a98589456ff9fe00db812 +size 4395730320 diff --git a/model-00034-of-00063.safetensors b/model-00034-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d2f25060d4549c7824675456f938e07a433fd8d --- /dev/null +++ b/model-00034-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e30b74b86263eeddaaf00fe724b93f2393229994c308add2bff5cdfa01c3b9 +size 4630578456 diff --git a/model-00035-of-00063.safetensors b/model-00035-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..709bd0073af5aab8646adf71a43aac2f5964d2dc --- /dev/null +++ b/model-00035-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bdb28a9420a8439a637939cf0454442a2a8053bfb559025a03e46ca624d10dc +size 4664165880 diff --git a/model-00036-of-00063.safetensors b/model-00036-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7912c0a239dc57408bcb65c0e840d729ebc6a91b --- /dev/null +++ b/model-00036-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f15b387e888a779cca0e0abdfb5a24f2e2a5a7d5eaa4f542740dc6d684eb2c +size 4395730320 diff --git a/model-00037-of-00063.safetensors b/model-00037-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..712444b11b84fd2b2cd1dce28a11c7ea364cc3b3 --- /dev/null +++ b/model-00037-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88144e23c401053e53cb95fa09e37f23b12e13e8f9e42f314088d1699857a3fb +size 4899014032 diff --git a/model-00038-of-00063.safetensors b/model-00038-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..965b671e3ca9c29caccf7c677ebd6717e1418f1d --- /dev/null +++ b/model-00038-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65612dcf558fd575dbefa93891f9bc782adb84b5f99470196d6b2faed19ac34d +size 4395730304 diff --git a/model-00039-of-00063.safetensors b/model-00039-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5956171381e9ae5a7eadda65685a1188426f4339 --- /dev/null +++ b/model-00039-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a0a963a21b94daf5a38a724d94760d5d0c9b158ce043b3c9e67511e30a82a4 +size 4395730320 diff --git a/model-00040-of-00063.safetensors b/model-00040-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f636496d89d32915545d117c20a99cea94a6678 --- /dev/null +++ b/model-00040-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ab29dd072503a9b582bf9a610d3b1986a3b087f248129ae02b90d77e282f65 +size 4899014032 diff --git a/model-00041-of-00063.safetensors b/model-00041-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..181977eaa39c4d4177934f35fca646807c5178ad --- /dev/null +++ b/model-00041-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328992287a9a3994ce1243a2049c17106556fe4b44a55c8450699f059f43e855 +size 4395730304 diff --git a/model-00042-of-00063.safetensors b/model-00042-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba78f713be7fc5f932ba514f9ef21a5dcc8fbd49 --- /dev/null +++ b/model-00042-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389abb00562ae9598e66a239f49548cf9f889e56326359b07307004fa9f8ed71 +size 4395730320 diff --git a/model-00043-of-00063.safetensors b/model-00043-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e8bf79435c97ebce4ef73bcf90b1fa715980310 --- /dev/null +++ b/model-00043-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f7e7aac7235b47d6b8574e777e302dddcdce13b66180a60c552dce71c7a38e +size 4630578456 diff --git a/model-00044-of-00063.safetensors b/model-00044-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef61a6b06928c8d1d3b7d20f3e13c9a947031ead --- /dev/null +++ b/model-00044-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393036a3bb94c6f552ee55727f06ae6e5941088ab0a6f979011ec52c77c8166c +size 4664165880 diff --git a/model-00045-of-00063.safetensors b/model-00045-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..407a8a1da3f0ecca1b7a0db3f62ac809471084ee --- /dev/null +++ b/model-00045-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c2c4bae0ed4b9f90c8b828921429d4de3b2fee1372098e1dbb39c2b0f48e64 +size 4395730320 diff --git a/model-00046-of-00063.safetensors b/model-00046-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5bcf19bf8730f7dcff6ef0f90e6e6174f5946fec --- /dev/null +++ b/model-00046-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c610235cf811d9369db85410d13c148f505487c354c99ba9f91d15499e570c2e +size 4630578456 diff --git a/model-00047-of-00063.safetensors b/model-00047-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f9bc2ba5985af5841faf46b55b8abdb0dd489ef --- /dev/null +++ b/model-00047-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c98db8fecdab4120c00cc6373917162aabbbf64eb798b3e6eecf09e1142307 +size 4664165888 diff --git a/model-00048-of-00063.safetensors b/model-00048-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1dfe58bc4add0352448890214ad1ccc0503e6bf --- /dev/null +++ b/model-00048-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29d921cebf00b007f07f8916c9f6d969e783fa897aba6a755bed2f7a1958db2 +size 4395730320 diff --git a/model-00049-of-00063.safetensors b/model-00049-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..684e38f37f182f9654d8128e6154d24784990e62 --- /dev/null +++ b/model-00049-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81be805c7e1c9e0765b7f4e41c71706f6d7cd9b2425c242c740b2884d6e2b647 +size 4630578456 diff --git a/model-00050-of-00063.safetensors b/model-00050-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..705f99a7f5f39b1ad43d6672af607fad2861b127 --- /dev/null +++ b/model-00050-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d966ea8d8f14fc6b4b7b9db34b50e14cb31f67fcc91ab5e084c959199ec6e30b +size 4664165880 diff --git a/model-00051-of-00063.safetensors b/model-00051-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19c35e462022610ad8cc988a4d4038c55dda74fd --- /dev/null +++ b/model-00051-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ee0a2934c7a355f05c86065c41b9e014f88cd0df87d175d19b651c7a51fea3 +size 4395730320 diff --git a/model-00052-of-00063.safetensors b/model-00052-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f67f52f3dd5c496e9b0a2030c1e0a6e690baef0 --- /dev/null +++ b/model-00052-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e551bdc2b99a89bb21869df464f208df7c93526912fdcfdf0a3fde50ac5bff77 +size 4630578448 diff --git a/model-00053-of-00063.safetensors b/model-00053-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b5925898288c0358086123bdfebb1ff36b5d26d --- /dev/null +++ b/model-00053-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929ce7ee8f2033529303315dbc89603b492c7793e736e2a4247cdc2975806fa6 +size 4664165888 diff --git a/model-00054-of-00063.safetensors b/model-00054-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6323fade803780faa4eb9562bf445c2b729960ac --- /dev/null +++ b/model-00054-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cfe89a7b7a319b5ff868559fe93a0b9d09a038a6948362aad2a9c910755ed2e +size 4395730320 diff --git a/model-00055-of-00063.safetensors b/model-00055-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdcf59ca105c76b4291d778279b298e07fd41ace --- /dev/null +++ b/model-00055-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1efddbb1fdf5a167151cfa5e1a823579250c2509ec3d9549bc39629bc82fcab +size 4630578456 diff --git a/model-00056-of-00063.safetensors b/model-00056-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c624db10cc239ff18da89496382b5045ef1b3da --- /dev/null +++ b/model-00056-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6b7dfc14469c976a0d83ee51f82061e407d20fc1dd6449744c77308c574c275 +size 4664165888 diff --git a/model-00057-of-00063.safetensors b/model-00057-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3afa2222808f0e1116cbc791bcab31a562083afb --- /dev/null +++ b/model-00057-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee804cf3f46f5a72028aebae6698451e0b5c9cef965c911967dd61d41123a4f +size 4395730320 diff --git a/model-00058-of-00063.safetensors b/model-00058-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d61be5d158ef25a5d38f8e34e7f4facb0bc46bf7 --- /dev/null +++ b/model-00058-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7ec824330818868424d1916569b7f9f8a9f0caee97a16c4334cc428df2cded +size 4630578456 diff --git a/model-00059-of-00063.safetensors b/model-00059-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e3965e2fbb920fbd4c0377fcc5357e579f38c67a --- /dev/null +++ b/model-00059-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9429e3ba3a22e3ae2f97d8ac29e22b35c2aa47d73d0a90ac3b6ad86d190e4f65 +size 4664165888 diff --git a/model-00060-of-00063.safetensors b/model-00060-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10fa9e56020cc8b6b0cf5a31827566171eded87d --- /dev/null +++ b/model-00060-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679a325c248a83110e49c791f68485dffaae55852cd9e82a873e455f00d9e6a8 +size 4395730320 diff --git a/model-00061-of-00063.safetensors b/model-00061-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcbdbca5ad7a5bc023eaa2f65257005bb98920db --- /dev/null +++ b/model-00061-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c5e286a8b0891ed5dc32e95d2be02d684024bfb4fd27029d409c6dc0ab96c0 +size 4899046904 diff --git a/model-00062-of-00063.safetensors b/model-00062-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20281d3c9079be0026ebf6ba21d179a47f73c032 --- /dev/null +++ b/model-00062-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca526a962ad9fbad7179bcb420ffcf3fbeb4f11ea74454d869f19101259b6f2 +size 4831970680 diff --git a/model-00063-of-00063.safetensors b/model-00063-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3dc383a3247bad1fe53f9177690cd63ebf56bb21 --- /dev/null +++ b/model-00063-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39dc1f2d183ea3b19c54585cbed700575d285fb56a9178903751714c4bdfc615 +size 3623977992 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b61455e3fc674a570635211d3198d209d2412d6a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00063.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00063.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00063.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00063.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00063.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00063.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00063.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00063.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00063.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00063.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00063.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00063.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00063.safetensors", "lm_head.weight": "model-00004-of-00063.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00063.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00063.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00063.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00063.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00063.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00063.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00063.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00063.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00063.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00063.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00063.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00063.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00063.safetensors", "model.embed_tokens.weight": "model-00007-of-00063.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00063.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00007-of-00063.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00063.safetensors", "model.layers.1.input_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00063.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00063.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00063.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00063.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.10.input_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00063.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00063.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00009-of-00063.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00063.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00063.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00063.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00063.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00063.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00063.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00010-of-00063.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00063.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00063.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00063.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00063.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00063.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00063.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00063.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00063.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00063.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00063.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00063.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00063.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00063.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00063.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00063.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00063.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00063.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00011-of-00063.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00063.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00012-of-00063.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00063.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00063.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00063.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00063.safetensors", "model.layers.15.input_layernorm.weight": "model-00012-of-00063.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00063.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00063.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00063.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00013-of-00063.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00063.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00063.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00063.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00063.safetensors", "model.layers.16.input_layernorm.weight": "model-00013-of-00063.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00063.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00063.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00063.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00013-of-00063.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00063.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00063.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00063.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00063.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00063.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00063.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00014-of-00063.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00063.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00063.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00063.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00063.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00063.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.18.input_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00063.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00063.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00063.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00015-of-00063.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00063.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00063.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00063.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00063.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00063.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00016-of-00063.safetensors", "model.layers.2.input_layernorm.weight": "model-00016-of-00063.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00016-of-00063.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00063.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00063.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00016-of-00063.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00063.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00063.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00016-of-00063.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00017-of-00063.safetensors", "model.layers.20.input_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00063.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00063.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00017-of-00063.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00063.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00063.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00017-of-00063.safetensors", "model.layers.21.input_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00017-of-00063.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00018-of-00063.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00018-of-00063.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00063.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00063.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00063.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00018-of-00063.safetensors", "model.layers.22.input_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00018-of-00063.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00063.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00063.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00063.safetensors", "model.layers.23.input_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00063.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00019-of-00063.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00019-of-00063.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00019-of-00063.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00063.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00063.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00020-of-00063.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00020-of-00063.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00020-of-00063.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00020-of-00063.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00020-of-00063.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00063.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00020-of-00063.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00020-of-00063.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00021-of-00063.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00021-of-00063.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00021-of-00063.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00021-of-00063.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00021-of-00063.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00021-of-00063.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00063.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00063.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00021-of-00063.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00021-of-00063.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00021-of-00063.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00021-of-00063.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00063.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00022-of-00063.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00063.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00022-of-00063.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00022-of-00063.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00022-of-00063.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00022-of-00063.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00022-of-00063.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00022-of-00063.safetensors", "model.layers.28.input_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00023-of-00063.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00023-of-00063.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00023-of-00063.safetensors", "model.layers.29.input_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00024-of-00063.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00024-of-00063.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00024-of-00063.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00024-of-00063.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00063.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00024-of-00063.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00024-of-00063.safetensors", "model.layers.3.input_layernorm.weight": "model-00024-of-00063.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00024-of-00063.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00024-of-00063.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00024-of-00063.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00024-of-00063.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00025-of-00063.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00025-of-00063.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00025-of-00063.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00025-of-00063.safetensors", "model.layers.30.input_layernorm.weight": "model-00025-of-00063.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00025-of-00063.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00025-of-00063.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00025-of-00063.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00025-of-00063.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00025-of-00063.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00025-of-00063.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00026-of-00063.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00026-of-00063.safetensors", "model.layers.31.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00026-of-00063.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00026-of-00063.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00026-of-00063.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00026-of-00063.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00026-of-00063.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00026-of-00063.safetensors", "model.layers.32.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00027-of-00063.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00027-of-00063.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00027-of-00063.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00027-of-00063.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00063.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00027-of-00063.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00027-of-00063.safetensors", "model.layers.33.input_layernorm.weight": "model-00027-of-00063.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00027-of-00063.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00027-of-00063.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00027-of-00063.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00027-of-00063.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00028-of-00063.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00028-of-00063.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00028-of-00063.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00028-of-00063.safetensors", "model.layers.34.input_layernorm.weight": "model-00028-of-00063.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00028-of-00063.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00028-of-00063.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00028-of-00063.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00028-of-00063.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00028-of-00063.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00028-of-00063.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00029-of-00063.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00029-of-00063.safetensors", "model.layers.35.input_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00029-of-00063.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00029-of-00063.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00029-of-00063.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00029-of-00063.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00029-of-00063.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00029-of-00063.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00029-of-00063.safetensors", "model.layers.36.input_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00029-of-00063.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00030-of-00063.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00030-of-00063.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00030-of-00063.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00030-of-00063.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00030-of-00063.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00030-of-00063.safetensors", "model.layers.37.input_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00030-of-00063.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00030-of-00063.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00063.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00031-of-00063.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00031-of-00063.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00031-of-00063.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00031-of-00063.safetensors", "model.layers.38.input_layernorm.weight": "model-00031-of-00063.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00031-of-00063.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00031-of-00063.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00031-of-00063.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00031-of-00063.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00031-of-00063.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00063.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00032-of-00063.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00032-of-00063.safetensors", "model.layers.39.input_layernorm.weight": "model-00032-of-00063.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00032-of-00063.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00032-of-00063.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00032-of-00063.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00032-of-00063.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00032-of-00063.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00032-of-00063.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00032-of-00063.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00032-of-00063.safetensors", "model.layers.4.input_layernorm.weight": "model-00032-of-00063.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00032-of-00063.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00033-of-00063.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00033-of-00063.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00033-of-00063.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00033-of-00063.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00033-of-00063.safetensors", "model.layers.40.input_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00033-of-00063.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00033-of-00063.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00034-of-00063.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00034-of-00063.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00034-of-00063.safetensors", "model.layers.41.input_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00034-of-00063.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00034-of-00063.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00034-of-00063.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00034-of-00063.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00034-of-00063.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00035-of-00063.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00035-of-00063.safetensors", "model.layers.42.input_layernorm.weight": "model-00035-of-00063.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00035-of-00063.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00035-of-00063.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00035-of-00063.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00035-of-00063.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00035-of-00063.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00035-of-00063.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00035-of-00063.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00035-of-00063.safetensors", "model.layers.43.input_layernorm.weight": "model-00035-of-00063.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00035-of-00063.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00036-of-00063.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00036-of-00063.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00036-of-00063.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00036-of-00063.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00036-of-00063.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00036-of-00063.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00036-of-00063.safetensors", "model.layers.44.input_layernorm.weight": "model-00036-of-00063.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00036-of-00063.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00036-of-00063.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00036-of-00063.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00036-of-00063.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00037-of-00063.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00037-of-00063.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00037-of-00063.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00037-of-00063.safetensors", "model.layers.45.input_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00037-of-00063.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00037-of-00063.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00037-of-00063.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00037-of-00063.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00037-of-00063.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00038-of-00063.safetensors", "model.layers.46.input_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00038-of-00063.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00038-of-00063.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00038-of-00063.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00038-of-00063.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00038-of-00063.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00038-of-00063.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00038-of-00063.safetensors", "model.layers.47.input_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00038-of-00063.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00039-of-00063.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00039-of-00063.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00039-of-00063.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00039-of-00063.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00039-of-00063.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00039-of-00063.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00039-of-00063.safetensors", "model.layers.48.input_layernorm.weight": "model-00039-of-00063.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00039-of-00063.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00039-of-00063.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00039-of-00063.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00039-of-00063.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00040-of-00063.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00040-of-00063.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00040-of-00063.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00040-of-00063.safetensors", "model.layers.49.input_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00040-of-00063.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00040-of-00063.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00040-of-00063.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00040-of-00063.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00040-of-00063.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00041-of-00063.safetensors", "model.layers.5.input_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00041-of-00063.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00041-of-00063.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00041-of-00063.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00041-of-00063.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00041-of-00063.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00041-of-00063.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00041-of-00063.safetensors", "model.layers.50.input_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00041-of-00063.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00042-of-00063.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00042-of-00063.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00042-of-00063.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00042-of-00063.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00042-of-00063.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00042-of-00063.safetensors", "model.layers.51.input_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00042-of-00063.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00042-of-00063.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00042-of-00063.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00043-of-00063.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00043-of-00063.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00043-of-00063.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00043-of-00063.safetensors", "model.layers.52.input_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00043-of-00063.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00043-of-00063.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00043-of-00063.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00043-of-00063.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00043-of-00063.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00044-of-00063.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00044-of-00063.safetensors", "model.layers.53.input_layernorm.weight": "model-00044-of-00063.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00044-of-00063.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00044-of-00063.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00044-of-00063.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00044-of-00063.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00044-of-00063.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00044-of-00063.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00044-of-00063.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00044-of-00063.safetensors", "model.layers.54.input_layernorm.weight": "model-00044-of-00063.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00044-of-00063.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00045-of-00063.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00045-of-00063.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00045-of-00063.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00045-of-00063.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00045-of-00063.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00045-of-00063.safetensors", "model.layers.55.input_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00045-of-00063.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00045-of-00063.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00045-of-00063.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00046-of-00063.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00046-of-00063.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00046-of-00063.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00046-of-00063.safetensors", "model.layers.56.input_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00046-of-00063.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00046-of-00063.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00046-of-00063.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00046-of-00063.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00046-of-00063.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00047-of-00063.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00047-of-00063.safetensors", "model.layers.57.input_layernorm.weight": "model-00047-of-00063.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00047-of-00063.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00047-of-00063.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00047-of-00063.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00047-of-00063.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00047-of-00063.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00047-of-00063.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00047-of-00063.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00047-of-00063.safetensors", "model.layers.58.input_layernorm.weight": "model-00047-of-00063.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00047-of-00063.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00048-of-00063.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00048-of-00063.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00048-of-00063.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00048-of-00063.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00048-of-00063.safetensors", "model.layers.59.input_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00048-of-00063.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00048-of-00063.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00049-of-00063.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00049-of-00063.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00049-of-00063.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00049-of-00063.safetensors", "model.layers.6.input_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00049-of-00063.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00049-of-00063.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00049-of-00063.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00049-of-00063.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00049-of-00063.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00050-of-00063.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00050-of-00063.safetensors", "model.layers.60.input_layernorm.weight": "model-00050-of-00063.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00050-of-00063.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00050-of-00063.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00050-of-00063.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00050-of-00063.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00050-of-00063.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00050-of-00063.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00050-of-00063.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00050-of-00063.safetensors", "model.layers.61.input_layernorm.weight": "model-00050-of-00063.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00050-of-00063.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00051-of-00063.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00051-of-00063.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00051-of-00063.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00051-of-00063.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00051-of-00063.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00051-of-00063.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00051-of-00063.safetensors", "model.layers.62.input_layernorm.weight": "model-00051-of-00063.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00051-of-00063.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00051-of-00063.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00051-of-00063.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00051-of-00063.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00052-of-00063.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00052-of-00063.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00052-of-00063.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00052-of-00063.safetensors", "model.layers.63.input_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00052-of-00063.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00052-of-00063.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00052-of-00063.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00052-of-00063.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00052-of-00063.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00053-of-00063.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00053-of-00063.safetensors", "model.layers.64.input_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00053-of-00063.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00053-of-00063.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00053-of-00063.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00053-of-00063.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00053-of-00063.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00053-of-00063.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00053-of-00063.safetensors", "model.layers.65.input_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00053-of-00063.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00054-of-00063.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00054-of-00063.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00054-of-00063.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00054-of-00063.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00054-of-00063.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.66.input_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00054-of-00063.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00054-of-00063.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00054-of-00063.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00055-of-00063.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00055-of-00063.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00055-of-00063.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00055-of-00063.safetensors", "model.layers.67.input_layernorm.weight": "model-00055-of-00063.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00055-of-00063.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00055-of-00063.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00055-of-00063.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00055-of-00063.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00055-of-00063.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00055-of-00063.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00056-of-00063.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00056-of-00063.safetensors", "model.layers.68.input_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00056-of-00063.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00056-of-00063.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00056-of-00063.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00056-of-00063.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00056-of-00063.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00056-of-00063.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00056-of-00063.safetensors", "model.layers.69.input_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00056-of-00063.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00057-of-00063.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00057-of-00063.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00057-of-00063.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00057-of-00063.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00057-of-00063.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00057-of-00063.safetensors", "model.layers.7.input_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00057-of-00063.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00057-of-00063.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00057-of-00063.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00058-of-00063.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00058-of-00063.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00058-of-00063.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00058-of-00063.safetensors", "model.layers.70.input_layernorm.weight": "model-00058-of-00063.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00058-of-00063.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00058-of-00063.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00058-of-00063.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00058-of-00063.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00058-of-00063.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00058-of-00063.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00059-of-00063.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00059-of-00063.safetensors", "model.layers.71.input_layernorm.weight": "model-00059-of-00063.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00059-of-00063.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00059-of-00063.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00059-of-00063.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00059-of-00063.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00059-of-00063.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00059-of-00063.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00059-of-00063.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00059-of-00063.safetensors", "model.layers.72.input_layernorm.weight": "model-00059-of-00063.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00059-of-00063.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00060-of-00063.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00060-of-00063.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00060-of-00063.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00060-of-00063.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00060-of-00063.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00060-of-00063.safetensors", "model.layers.73.input_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00060-of-00063.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00060-of-00063.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00060-of-00063.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00061-of-00063.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00061-of-00063.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00061-of-00063.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00061-of-00063.safetensors", "model.layers.74.input_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00061-of-00063.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00061-of-00063.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00061-of-00063.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00061-of-00063.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00061-of-00063.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00061-of-00063.safetensors", "model.layers.75.input_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00062-of-00063.safetensors", "model.layers.76.input_layernorm.weight": "model-00062-of-00063.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00062-of-00063.safetensors", "model.layers.77.input_layernorm.weight": "model-00062-of-00063.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00062-of-00063.safetensors", "model.layers.78.input_layernorm.weight": "model-00062-of-00063.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00062-of-00063.safetensors", "model.layers.79.input_layernorm.weight": "model-00062-of-00063.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00063-of-00063.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00063-of-00063.safetensors", "model.layers.8.input_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00063-of-00063.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.input_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00063-of-00063.safetensors", "model.norm.weight": "model-00063-of-00063.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c68051fe3c4d23234a59316bc52d21f6e3a4182c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}