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..791af8cbea9e222dc3519d27b94daba3e2160a99 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +base_model: +- NaniDAO/Llama-3.3-70B-Instruct-ablated +- huihui-ai/Llama-3.3-70B-Instruct-abliterated +- nbeerbower/Llama-3.1-Nemotron-lorablated-70B +- SentientAGI/Dobby-Unhinged-Llama-3.3-70B +- SicariusSicariiStuff/Negative_LLAMA_70B +library_name: transformers +tags: +- mergekit +- merge + +--- +# Cornerstone-0.1-LLaMA-70B + +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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [huihui-ai/Llama-3.3-70B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated) as a base. + +### Models Merged + +The following models were included in the merge: +* [NaniDAO/Llama-3.3-70B-Instruct-ablated](https://huggingface.co/NaniDAO/Llama-3.3-70B-Instruct-ablated) +* [nbeerbower/Llama-3.1-Nemotron-lorablated-70B](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B) +* [SentientAGI/Dobby-Unhinged-Llama-3.3-70B](https://huggingface.co/SentientAGI/Dobby-Unhinged-Llama-3.3-70B) +* [SicariusSicariiStuff/Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated +merge_method: sce +dtype: float32 +models: + - model: SicariusSicariiStuff/Negative_LLAMA_70B + - model: NaniDAO/Llama-3.3-70B-Instruct-ablated + - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B + - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B + +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4fa1dd7e71dd5bcadd3ff30062b13b737cd8008f --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "_name_or_path": "huihui-ai/Llama-3.3-70B-Instruct-abliterated", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "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": "4.49.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..cd857773e3694375d9e4d223521d553e24268ce4 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,8 @@ +base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated +merge_method: sce +dtype: float32 +models: + - model: SicariusSicariiStuff/Negative_LLAMA_70B + - model: NaniDAO/Llama-3.3-70B-Instruct-ablated + - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B + - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f683d9c33b4d48600888d7d38b7633f4ed042156 --- /dev/null +++ b/model-00001-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2073cef28afd5057812d2c068f5c0a9463f18709f41198dff8eef2e1893b0a25 +size 4202692736 diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56516e5ac712c2ac5253216ae54dca68eab9b0fc --- /dev/null +++ b/model-00002-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca74ebe02d6021361bae82b3aaec01aadac9634695b6a9157caec67136723e1 +size 4202725624 diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4361cdaba9717570606ee58602120ef9c4e9d273 --- /dev/null +++ b/model-00003-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a024b07834c73d22c8f776518e915e811c7e46aa66b95984c498599e1943b571 +size 4362142872 diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73eaf55cc15cc30be2f98497b0cf9774dfaa1468 --- /dev/null +++ b/model-00004-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc265c8729102049a5049cb008971aac233c99f7b679836c47f986dec75f94ee +size 4362142880 diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc7d1092b174d6057a89a984dafc8b1960a24e6e --- /dev/null +++ b/model-00005-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8e91e535b87ec78da30e428e19edcb39e9cc8b68ac9ecca12a079ee9be17ae +size 4966188888 diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c5860592cb31b5bca914c6de22cc7e8cfcee261 --- /dev/null +++ b/model-00006-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06081560e3e1f059b1e6aee84d5b05dc34d45289f4496caceba68739fe11b41a +size 4362142888 diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..313b426eeb11b9d78f9b32232bda2173cc411ac4 --- /dev/null +++ b/model-00007-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bc1e3fa22c17c65c8ea69fc03e70818128f33aaabb9c06ff106d063420d241 +size 4362142888 diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b638f1c314bbd297d8dde90d18ee65d8000c527c --- /dev/null +++ b/model-00008-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1e702fbccc209944ac4383fec39e6c557f16b41a29d96784299119890211f4 +size 4966188888 diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47b3360120c7ce4e16dae7dda8606297d9dee2f3 --- /dev/null +++ b/model-00009-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f181597462fdd54e755ee0c29fa3e62b68a41c4dfb97ee6bf318f63218566f +size 4362142888 diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b515852b36f16f3896d711dee5dc510b74c70e03 --- /dev/null +++ b/model-00010-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b551e41e21267deb665beb7a597ee568fc4384bc731f7cd636002eda078c988 +size 4362142888 diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f5e0a97adbd186e335196dd3396ffded916aff5c --- /dev/null +++ b/model-00011-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90119e5c0f2595b118ca834242a4945b92a672234f111b8b61bee0d4c48b0aa9 +size 4966188888 diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..188d0821c91b8201c7fee49d2f1d9b8ea3858b4c --- /dev/null +++ b/model-00012-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a369efcfbf6d56e549ec34714aa2b08fbb0bc1e8d1dbce2a331eb62dfc82bf9 +size 4362142880 diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b11b0bea6fa479fd5f5fd86b3b92e8b4f0181683 --- /dev/null +++ b/model-00013-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e56195bb2adadf6a5cbaca761ba4116f28319a206ed9db0a94541809d2627179 +size 4362142888 diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2e58e216377f565f75379a951dc16a6b47f4521 --- /dev/null +++ b/model-00014-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1c7c71a958412ee95bbd3489da4ff21eb85e699a9a1e84ce6b6005a3d88e01 +size 4966188888 diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4c0023f24be3289641138ab733edfd4291bc644 --- /dev/null +++ b/model-00015-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108098063eee848b12e120a84f59919ab85b2605a2c80bbddbff8aab686ff90c +size 4362142888 diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cda84738eb582c78880727ef583c9fc3717106b --- /dev/null +++ b/model-00016-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5b2df5951d8145f8530715a2d9749f0a6c0a1cf5d6b32cf465609d570a6293 +size 4362142888 diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be988018014efca0f59755e4053ca30af28a7327 --- /dev/null +++ b/model-00017-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00cb1b87c7a36dab58198594234d1a86427e8d2296d15b0ab28bbd3afd48eaae +size 4966188888 diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..861f777a2fdac88f98b17c31f8f0beaf39e21136 --- /dev/null +++ b/model-00018-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501902ecce966c1133d205edefa0d94a355d05a229284b83868a8a700513216e +size 4362142888 diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f09cf80fb4bf182438c6249131b51349fae7ba74 --- /dev/null +++ b/model-00019-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38bd876c2afba75b1115bfe9fed0d0ef161c81c91c3ff10e7e6fb98589799e44 +size 4362142888 diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9499807833f88cc8802f68e254f65bf2bda5197 --- /dev/null +++ b/model-00020-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2daa7e1dee3a43893f33b638667467a1f03f033df741566dcc88d4b33ba1f5 +size 4966188880 diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1c483420f6e47f89cb1493e2be53e3d8adfb479 --- /dev/null +++ b/model-00021-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dac80f67ec868608bbf232380e6fe62638b9fbcf5ada5fe08b7c5f83fdbfb1b +size 4362142888 diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8856ac46a61bbbeb43d91a2937c66312ebff6207 --- /dev/null +++ b/model-00022-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f3b583fde984b6e758f75cee78cb1abef33e69b968bf333c320fc41339c54f +size 4362142888 diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae6eb3f118c38f1f0207b217193e81903e62b09e --- /dev/null +++ b/model-00023-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe9ec4011af65459d6a745e71638ab8e14615a06713053d2ed4c9a2d93ea2b2 +size 4966188888 diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b54236cc695ff25b53a908979250b18c68160a44 --- /dev/null +++ b/model-00024-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aab762bcbc306eaf5fd1e2194dd1c3f0e9b4ad3a1ac50da13354d91e9b888b6 +size 4362142888 diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5dad8e1a40d5cbe1abe4ee3c6bc2a9bfa191a1cc --- /dev/null +++ b/model-00025-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3636a1e4e9e382655587d7332ee776510cc13bf05c6812200afe2cc3ddde881 +size 4362142888 diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..327da04b2f3fa191c6e6253003eafb3929a879ad --- /dev/null +++ b/model-00026-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf0b09783bd001d38e5c3bead2d06f686db30120ae16bed744a00113f2d245f7 +size 4966188888 diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13baf9200a53911b9eb398fa175fcc57dc7becaf --- /dev/null +++ b/model-00027-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d69440aaaac26ed4f6c8c6c9198222ad79787db25402d70ca8f97416ab8f2e +size 4362142888 diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7a09745c984bd9bbd2b634f7aa3edc1bca56dd8 --- /dev/null +++ b/model-00028-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db834c0a56ac0891f8b35f30b0a81644a101727e851efa88bc953a26b64f064 +size 4362142880 diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46ca1bb04609a9177089ac011de32626c618b3c1 --- /dev/null +++ b/model-00029-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6144576ef6e29fea7a7b79e94da3a8c8fa4ae5fe88c3a7df1fa60d9534d63b6 +size 4966188888 diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42204c5986db612fed34b79c362f3ef5a1a3277b --- /dev/null +++ b/model-00030-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0735bf8ebdec7128e09e969bc347e508e9458f281dbbcd60a9ac061d223ce528 +size 4362142888 diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17cb92577753667125d20caea7df36e196f9b999 --- /dev/null +++ b/model-00031-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:034881e3720b0eb79e506f239ba1273c96a45f1026cc6d055e004d142c2eebd5 +size 4362142888 diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f5ea78874d8c4bab53aa5425f428fc32d1d6bea --- /dev/null +++ b/model-00032-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d506c49fb05f1d8a46341d5ef25da20fc16c07fda0c5eab4e7bdcdd29b17f1 +size 4966188888 diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71c0bea4c1c559f7de09b3a88fd2f4fda2130726 --- /dev/null +++ b/model-00033-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c392dda46768b8cbc97b37099f5230ac89f3b2894f7a3de303fdc2c5c497cf76 +size 4362142888 diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f29d08713053566b904057ed3ed0309e723b840 --- /dev/null +++ b/model-00034-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40c18e810e7d450d0fe001ef7d968587b4d6c884cb1248db0e750bd5ba06f7f +size 4362142888 diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f36a484c52ca60cc345054a6d0240436af7bacf7 --- /dev/null +++ b/model-00035-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafcf16de1968a82051c2883feb29111799f204fef6032e258347402bbfaf287 +size 4966188888 diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0846715caf04f65644a3e76297dbe5ca60615a12 --- /dev/null +++ b/model-00036-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08041dbf9c10182e5b6f5c8a7b2d0493488f9981587840989f117c94f3d8f6ba +size 4362142880 diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5029b9e3b4959c2a1d3aa6d6efd6b74af23b9a28 --- /dev/null +++ b/model-00037-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:143734ff56745ced89b0ca9f60da662e7c484e1af5d62be753fb90514f3819d2 +size 4362142880 diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..231abba6c728cb67676fbe1128d3eb96f835feac --- /dev/null +++ b/model-00038-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85084fcea04a4883d3a83f296f5fcc010b247cfe0c11329dcae6a71949abc525 +size 4966188888 diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c06d9918291099dd2ba408e26289bafc51e67d87 --- /dev/null +++ b/model-00039-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a1b98d21ea213c0ee55a7972ce8964bf50c702340b4b9924278c9ca5f7802a +size 4362142888 diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c66e61debf5d4bc153c4b84180b05f5130aa5d1b --- /dev/null +++ b/model-00040-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee66d06c5f22b84a71e56fedb160d4f08bc9b1fcccf577946941d8a7f28187f +size 4362142888 diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc5ad42c18367754f08e64297a8fa1a433d846fb --- /dev/null +++ b/model-00041-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a41129ff14b573ec3a77c1688d3ce8dc536d4febc66f69a1ad79ac9303399c0 +size 4966188888 diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da4bcea786bc688bb21307ec291a2b69700c7c04 --- /dev/null +++ b/model-00042-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0f6375b24c952a85f2d76cd4a11a9ab42afb8810b0e9080b8be15334e98d41 +size 4362142888 diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c6cbdcabe564f1ba8d58d47b9a0f065e9266100 --- /dev/null +++ b/model-00043-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c292515cc453b2795255964f2cafac0c69c65d5825568b9492202311317b86 +size 4362142888 diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c92fd65259e7fc122416b204e85181d61d83b755 --- /dev/null +++ b/model-00044-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e6cf995d3d78a8c13077973e2a939df327e0cd09bf3275abbd47c9f00c116a +size 4966188888 diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..43d20ca45bc8410bf4207e7c8610eba75030197b --- /dev/null +++ b/model-00045-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf3d5fc78269aef44724b8e680a2ae6e2ab67dc4294c09c9ea9b0314725d605 +size 4362142880 diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..722bc9eedacdf706adf9387d573743dcd1cce2c4 --- /dev/null +++ b/model-00046-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aae2bf7069a8f8c7cef530fd55098343d84f7586b25eb45569a8ed3be25f875 +size 4362142888 diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e5b7dd3294344493dbe68ae22cdec168fe461bb --- /dev/null +++ b/model-00047-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d310ad7ab5c4a182b30647b72998fc963240578cb9b93e0cbe531b17f3625172 +size 4966188888 diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f048efaf19f93224c93d75779e13eac8805fd08 --- /dev/null +++ b/model-00048-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44815b6bc23427b9222a85654ea73496a9a337b9f3fa6f6667a7ca0b3458af94 +size 4362142888 diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e045076538d1aa66c2a173a329f67cf8b6b849d3 --- /dev/null +++ b/model-00049-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed6358248da5b507e1361167f177f416b2bb01bdd6a427f263e0810c50e8d60 +size 4362142888 diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b92278dbe472334d84ffaba40d2ac9ffd13f63d --- /dev/null +++ b/model-00050-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7e6700461732240288384f5b7b2e6cee21a3979953b5c0549b26722b58bb98 +size 4966188888 diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ecec45d020b72bd3293e8337ffd63ba3dc6083e4 --- /dev/null +++ b/model-00051-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b98af27795ba4b3c3f7a79d21dd37a64d859ce6df4e4503d7d6c8b7c8403c1c +size 4362142888 diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f8455d39400eee53e83bc9c5de6b6c90064dae0 --- /dev/null +++ b/model-00052-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488966434f503dd98df8ceb9469b069c69f2e5b35ea33ab3148f4097040752ec +size 4362142888 diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d68ad213bff4697624bbb53044fc74075c5b297 --- /dev/null +++ b/model-00053-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12481de144e1795f8e3e9d8d190ee4f584ddd3a5ba1ebf7ca63cab437c94a517 +size 4966188880 diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c09377881eb1242b09b5b3440fcd2cb5eaee711 --- /dev/null +++ b/model-00054-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9abe03ebe13bf16aa9f983c2f44e5b9177ad87daaff6e83a4f805cf518a2a3ac +size 4362142888 diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..abe7c7cbf57a39f8f74f09fde377fed0c070e66c --- /dev/null +++ b/model-00055-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d9ad8dae16639737aa6711b64e056a0d7c39809cae15203dfa04b0dbfc1085 +size 4362142888 diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a04d220ce114334dc2389412a405daf50b35336d --- /dev/null +++ b/model-00056-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecba772407284554b729870f0db40e0da806faec6634ff85bf4d311504c9d1fb +size 4966188888 diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4cf1b41c5ecdba6a629983ce298f1111cf9ee7d7 --- /dev/null +++ b/model-00057-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114cafaf081386b5bc6a4f713855acfe4b4e2b74591c5f2d2a77bde9e3c776b7 +size 4362142888 diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..604ffee6ea2d9547c119dfdb423d4fde0d727921 --- /dev/null +++ b/model-00058-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53870bbb56347cb0679711e2d376d6d1bd01adbef34714d27bcb88e858ca82c7 +size 4362142888 diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..813c4ae6bf061082097ab9908c7df553abdb85ef --- /dev/null +++ b/model-00059-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46548dd7af1ce591b40bd971cc2f3e4da85aef1a67c2c953c4f6af972a0da46 +size 4966188888 diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da543e30ce81a0ac08b65dadbc0d487b2e6160d6 --- /dev/null +++ b/model-00060-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7627c6508ebb0385a417ae119f893c3ba9f958d6699791b68bd8eecfcde5d3 +size 4362142888 diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f2d7fe21214be1d8e74b87ad6a43abe2644e77f --- /dev/null +++ b/model-00061-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b306f0d5049151f78fc6a75feb5d1bbcbf5862775d11918657dada9acd4c53c5 +size 4362142880 diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..374187f7974c2e3b2341f1bd7609284e987e796c --- /dev/null +++ b/model-00062-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325aa268d03de4a7cb7254f29e680787cf31672aeb5e4b0ba1ac1f935430b2e6 +size 4966188856 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..37a5d995fd8640b814a79fcc9517efd56e2de1bb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.1"}, "weight_map": {"lm_head.weight": "model-00001-of-00062.safetensors", "model.embed_tokens.weight": "model-00002-of-00062.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00062.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00062.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00062.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00062.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00062.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00062.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00062.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00062.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00062.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00062.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00062.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00062.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00062.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00062.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00062.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00062.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00062.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00062.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00062.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00062.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00062.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00062.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00062.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00062.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00062.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00062.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00062.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00062.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00062.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.input_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00062.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00023-of-00062.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.input_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.input_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.input_layernorm.weight": "model-00025-of-00062.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00026-of-00062.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.input_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.input_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.input_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00028-of-00062.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00062.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00029-of-00062.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.input_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", "model.layers.41.input_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00030-of-00062.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00030-of-00062.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00062.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.input_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", "model.layers.43.input_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00031-of-00062.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00032-of-00062.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.input_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.input_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", "model.layers.46.input_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00033-of-00062.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00034-of-00062.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", "model.layers.47.input_layernorm.weight": "model-00034-of-00062.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00034-of-00062.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00035-of-00062.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.input_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", "model.layers.49.input_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00036-of-00062.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00036-of-00062.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00036-of-00062.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", "model.layers.5.input_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00036-of-00062.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00037-of-00062.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", "model.layers.50.input_layernorm.weight": "model-00037-of-00062.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00037-of-00062.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00038-of-00062.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.input_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", "model.layers.52.input_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", "model.layers.53.input_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00039-of-00062.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00040-of-00062.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", "model.layers.54.input_layernorm.weight": "model-00040-of-00062.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00040-of-00062.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00041-of-00062.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.input_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", "model.layers.56.input_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00042-of-00062.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00042-of-00062.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00042-of-00062.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00042-of-00062.safetensors", "model.layers.57.input_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00042-of-00062.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00043-of-00062.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", "model.layers.58.input_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00043-of-00062.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00044-of-00062.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.input_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.input_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00045-of-00062.safetensors", "model.layers.60.input_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00045-of-00062.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00046-of-00062.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", "model.layers.61.input_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00046-of-00062.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00047-of-00062.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.input_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", "model.layers.63.input_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00048-of-00062.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00048-of-00062.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00048-of-00062.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00048-of-00062.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00048-of-00062.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", "model.layers.64.input_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00048-of-00062.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00049-of-00062.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", "model.layers.65.input_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00049-of-00062.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00050-of-00062.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.input_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", "model.layers.67.input_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", "model.layers.68.input_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00051-of-00062.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00052-of-00062.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", "model.layers.69.input_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00052-of-00062.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00053-of-00062.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.input_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", "model.layers.70.input_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00054-of-00062.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00054-of-00062.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00054-of-00062.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00062.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00054-of-00062.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00054-of-00062.safetensors", "model.layers.71.input_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00054-of-00062.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00055-of-00062.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", "model.layers.72.input_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00055-of-00062.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00056-of-00062.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.input_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", "model.layers.74.input_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00057-of-00062.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00062.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00057-of-00062.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00057-of-00062.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00062.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00062.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00057-of-00062.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00062.safetensors", "model.layers.75.input_layernorm.weight": "model-00057-of-00062.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00057-of-00062.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00058-of-00062.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", "model.layers.76.input_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00058-of-00062.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00059-of-00062.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.input_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", "model.layers.78.input_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00060-of-00062.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00060-of-00062.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00060-of-00062.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", "model.layers.79.input_layernorm.weight": "model-00060-of-00062.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00060-of-00062.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00062.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.8.input_layernorm.weight": "model-00061-of-00062.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00061-of-00062.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00062-of-00062.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.input_layernorm.weight": "model-00062-of-00062.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.norm.weight": "model-00062-of-00062.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..cc6faec1a4b11893eb15700e2a5743aa79fa107e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "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|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "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": "PreTrainedTokenizer" +}