From 7c32e3a66eb31f12ce709d59931989083f132a6c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 26 Oct 2026 18:42:21 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: fblgit/UNA-SimpleSmaug-34b-v1beta Source: Original Platform --- .gitattributes | 37 +++ README.md | 283 ++++++++++++++++ config.json | 29 ++ generation_config.json | 7 + model-00001-of-00015.safetensors | 3 + model-00002-of-00015.safetensors | 3 + model-00003-of-00015.safetensors | 3 + model-00004-of-00015.safetensors | 3 + model-00005-of-00015.safetensors | 3 + model-00006-of-00015.safetensors | 3 + model-00007-of-00015.safetensors | 3 + model-00008-of-00015.safetensors | 3 + model-00009-of-00015.safetensors | 3 + model-00010-of-00015.safetensors | 3 + model-00011-of-00015.safetensors | 3 + model-00012-of-00015.safetensors | 3 + model-00013-of-00015.safetensors | 3 + model-00014-of-00015.safetensors | 3 + model-00015-of-00015.safetensors | 3 + model.safetensors.index.json | 550 +++++++++++++++++++++++++++++++ special_tokens_map.json | 30 ++ tokenizer.model | 3 + tokenizer_config.json | 43 +++ unasimple.png | 3 + 24 files changed, 1030 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00015.safetensors create mode 100644 model-00002-of-00015.safetensors create mode 100644 model-00003-of-00015.safetensors create mode 100644 model-00004-of-00015.safetensors create mode 100644 model-00005-of-00015.safetensors create mode 100644 model-00006-of-00015.safetensors create mode 100644 model-00007-of-00015.safetensors create mode 100644 model-00008-of-00015.safetensors create mode 100644 model-00009-of-00015.safetensors create mode 100644 model-00010-of-00015.safetensors create mode 100644 model-00011-of-00015.safetensors create mode 100644 model-00012-of-00015.safetensors create mode 100644 model-00013-of-00015.safetensors create mode 100644 model-00014-of-00015.safetensors create mode 100644 model-00015-of-00015.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json create mode 100644 unasimple.png diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f16836c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +image[[:space:]](31).png filter=lfs diff=lfs merge=lfs -text +unasimple.png filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bcb09ec --- /dev/null +++ b/README.md @@ -0,0 +1,283 @@ +--- +license: apache-2.0 +tags: +- UNA +- simple-math +- juanako +base_model: abacusai/Smaug-34B-v0.1 +datasets: +- fblgit/simple-math +- jondurbin/bagel-v0.3 +model-index: +- name: UNA-SimpleSmaug-34b-v1beta + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: AI2 Reasoning Challenge (25-Shot) + type: ai2_arc + config: ARC-Challenge + split: test + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 74.57 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag (10-Shot) + type: hellaswag + split: validation + args: + num_few_shot: 10 + metrics: + - type: acc_norm + value: 86.74 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU (5-Shot) + type: cais/mmlu + config: all + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 76.68 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: TruthfulQA (0-shot) + type: truthful_qa + config: multiple_choice + split: validation + args: + num_few_shot: 0 + metrics: + - type: mc2 + value: 70.17 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-shot) + type: winogrande + config: winogrande_xl + split: validation + args: + num_few_shot: 5 + metrics: + - type: acc + value: 83.82 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8k (5-shot) + type: gsm8k + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 72.48 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: IFEval (0-Shot) + type: HuggingFaceH4/ifeval + args: + num_few_shot: 0 + metrics: + - type: inst_level_strict_acc and prompt_level_strict_acc + value: 45.56 + name: strict accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: BBH (3-Shot) + type: BBH + args: + num_few_shot: 3 + metrics: + - type: acc_norm + value: 32.78 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MATH Lvl 5 (4-Shot) + type: hendrycks/competition_math + args: + num_few_shot: 4 + metrics: + - type: exact_match + value: 0.15 + name: exact match + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GPQA (0-shot) + type: Idavidrein/gpqa + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 8.95 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MuSR (0-shot) + type: TAUR-Lab/MuSR + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 11.96 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU-PRO (5-shot) + type: TIGER-Lab/MMLU-Pro + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 39.33 + name: accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta + name: Open LLM Leaderboard +--- + +# UNA-SimpleSmaug-34b-v1beta + +Scoring 04-February-2024 #1 34B model, outperforming its original base model Smaug-34B-v0.1 with `77.41` 😎 +Oh, btw.. this one went thru SFT so the abacus inside Smaug is back to normal.. so you can further train/dpo him .. RESET!.. + +*UPDATES* March : Stills undisputed 34B King + Smaug 70B stills undisputed 70B King + +==== +And people wonders.. why there is no UNA of Hermes or Smaug 70B? << i dont think is worth the time to spend on a model that is widely known for not being too useful, likely UNA can fix some of the internal mess.. +for Hermes, we spoke chitchat quick a couple times but nothing solid, but we would like to make a reborn of excellent models using UNA, just liek we did with UNA-Dolphin where we saw +relevant performance is short time. +=== + +![UNA](https://huggingface.co/fblgit/UNA-SimpleSmaug-34b-v1beta/resolve/main/unasimple.png) +Applied UNA only on the Attention, not on the MLP's +* Is based on Smaug +* SimpleMath dataset +* It was trained on Axolotl + +## Experiment +The thing here is to understand whats the impact of SimpleMath applied at the attention layer during a SFT session and how it impacts on the neural network overall. + +Results: Improving mathematican and reasoning capabilities without degrading and presserving previous training sessions. + +**And enjoy our ModelSimilarities tool detector** https://github.com/fblgit/model-similarity where we confirmed numerically the bloodties of the model. +## Evals + + +| Metric |Value| +|---------------------------------|----:| +|Avg. |77.41| +|AI2 Reasoning Challenge (25-Shot)|74.57| +|HellaSwag (10-Shot) |86.74| +|MMLU (5-Shot) |76.68| +|TruthfulQA (0-shot) |70.17| +|Winogrande (5-shot) |83.82| +|GSM8k (5-shot) |72.48| + +``` +| Task |Version| Metric |Value | +|-------------|------:|--------|----------------:| +|arc_challenge| HF|acc_norm| 0.7457337883959 | +|gsm8k | HF|acc | 0.7247915087187 | +|mmlu | HF|acc | 0.7649553475572 | +|mmlu | HF|acc_norm| 0.7681713551647 | +|hellaswag | HF|acc_norm| 0.8673571001792 | +|truthfulqa | HF|mc2 | 0.7016557407771 | +|winogrande | HF|acc | 0.8382004735595 | +|------------------------------------------------| +``` + +Increasing GSM, MMLU, ARC, WINO. + +## Citations +To abacusai for making Smaug-34B, the Bagel, and all the magic behind the base model. + +**If you use the model, provide citation even for merges or anything.** +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__UNA-SimpleSmaug-34b-v1beta) + + + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__UNA-SimpleSmaug-34b-v1beta) + +| Metric |Value| +|-------------------|----:| +|Avg. |23.12| +|IFEval (0-Shot) |45.56| +|BBH (3-Shot) |32.78| +|MATH Lvl 5 (4-Shot)| 0.15| +|GPQA (0-shot) | 8.95| +|MuSR (0-shot) |11.96| +|MMLU-PRO (5-shot) |39.33| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..e870461 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "abacusai/Smaug-34B-v0.1", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 7168, + "initializer_range": 0.02, + "intermediate_size": 20480, + "max_position_embeddings": 32768, + "model_type": "llama", + "num_attention_heads": 56, + "num_hidden_layers": 60, + "num_key_value_heads": 8, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0.dev0", + "use_cache": true, + "vocab_size": 64000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..dd21a64 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.37.0.dev0" +} diff --git a/model-00001-of-00015.safetensors b/model-00001-of-00015.safetensors new file mode 100644 index 0000000..452bacc --- /dev/null +++ b/model-00001-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e715ec8bc876fc748f4b75a51eafdc2c74a6fb8c77e80f9f4c496c9d63f975 +size 4793130760 diff --git a/model-00002-of-00015.safetensors b/model-00002-of-00015.safetensors new file mode 100644 index 0000000..3a3d92a --- /dev/null +++ b/model-00002-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b7b25fda46595868b10894270e98eedc1aa9961278d8a9db16333cd2014ae0 +size 4756459720 diff --git a/model-00003-of-00015.safetensors b/model-00003-of-00015.safetensors new file mode 100644 index 0000000..9c9110c --- /dev/null +++ b/model-00003-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b0ae414d060e44f40b306ae813a6dadd25dca7693219ac49ac0d66fa2d145e +size 4991370136 diff --git a/model-00004-of-00015.safetensors b/model-00004-of-00015.safetensors new file mode 100644 index 0000000..3f94cc1 --- /dev/null +++ b/model-00004-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f515e929406e8c76456e367fc1039f593b7518b31896f7e3f75b81ed8ee71f07 +size 4756459760 diff --git a/model-00005-of-00015.safetensors b/model-00005-of-00015.safetensors new file mode 100644 index 0000000..091e238 --- /dev/null +++ b/model-00005-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ad2535534e6aacff92b51c089399e8eacd9f9fcf8393df31d158bca0e18159 +size 4756459760 diff --git a/model-00006-of-00015.safetensors b/model-00006-of-00015.safetensors new file mode 100644 index 0000000..6e2162d --- /dev/null +++ b/model-00006-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a3dd3c8cd5c5344678a291821b85b9f4fa9827a2731d334bed2c4a58c95131 +size 4991370160 diff --git a/model-00007-of-00015.safetensors b/model-00007-of-00015.safetensors new file mode 100644 index 0000000..347d4cc --- /dev/null +++ b/model-00007-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45eb64519de4bd2d9422927c5e2014f27cf5c67c029f9ee6a19361bcda7ee0f9 +size 4756459760 diff --git a/model-00008-of-00015.safetensors b/model-00008-of-00015.safetensors new file mode 100644 index 0000000..29af32c --- /dev/null +++ b/model-00008-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05177e04a72206d993cb5b0f874005faae08fc3a98630a24da65654987633263 +size 4756459760 diff --git a/model-00009-of-00015.safetensors b/model-00009-of-00015.safetensors new file mode 100644 index 0000000..7eecde8 --- /dev/null +++ b/model-00009-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b4ef1952c44b1a417035d9d93e70f9e45a83496b0881f9dcf7e0a5d553330b +size 4991370160 diff --git a/model-00010-of-00015.safetensors b/model-00010-of-00015.safetensors new file mode 100644 index 0000000..71370d4 --- /dev/null +++ b/model-00010-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2cc98492d546de6620b831319ce0cf87f088ba4e5f3993eebb3003a5b4196dd +size 4756459760 diff --git a/model-00011-of-00015.safetensors b/model-00011-of-00015.safetensors new file mode 100644 index 0000000..0802718 --- /dev/null +++ b/model-00011-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f224a0f6f3fbd4b201781e65fa7a4a07bb6cfedf44b7ecd9dcf96f457d84225c +size 4756459760 diff --git a/model-00012-of-00015.safetensors b/model-00012-of-00015.safetensors new file mode 100644 index 0000000..d477a98 --- /dev/null +++ b/model-00012-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d2dd82ef89d4e2fa91753477affabcec0aa15bdc4fe669af37d1a7601c7724 +size 4991370160 diff --git a/model-00013-of-00015.safetensors b/model-00013-of-00015.safetensors new file mode 100644 index 0000000..27ab63c --- /dev/null +++ b/model-00013-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ffa32f1064d78955d76533af440cd3aca081a8bdd5a256b7c0281c234d46ba +size 4756459760 diff --git a/model-00014-of-00015.safetensors b/model-00014-of-00015.safetensors new file mode 100644 index 0000000..e4a93a6 --- /dev/null +++ b/model-00014-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda79867b8aef0835c1e5c60432df865409a8e381730d62b8fbf64519b22fd6b +size 4756459760 diff --git a/model-00015-of-00015.safetensors b/model-00015-of-00015.safetensors new file mode 100644 index 0000000..924f769 --- /dev/null +++ b/model-00015-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0007f5c71116f755a16cee9b3311bae66dbf6766b2949bdcec38b9ee02795b8 +size 1211148856 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..1d3fe2b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,550 @@ +{ + "metadata": { + "total_size": 68777834496 + }, + "weight_map": { + "lm_head.weight": "model-00015-of-00015.safetensors", + "model.embed_tokens.weight": "model-00001-of-00015.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", + "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", + "model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", + "model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", + "model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", + "model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", + "model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", + "model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", + "model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", + "model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", + "model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", + "model.norm.weight": "model-00015-of-00015.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8bedc05 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8306c82 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39 +size 1033105 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..8e40fc3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <>\\n' + messages[idx]['content'] + '\\n<>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1024, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/unasimple.png b/unasimple.png new file mode 100644 index 0000000..e899ac7 --- /dev/null +++ b/unasimple.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27069602e388062546a858e5afabf8f3694a88e265afd5bab16bc6bbdaac64c +size 1534030