commit 995af08d5d5ac2343d2f415f4f4ea979381c186b Author: ModelHub XC Date: Mon May 11 10:34:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: KOREAson/KO-REAson-G3-4B-0831 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..303367b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer_config.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..41612cf --- /dev/null +++ b/README.md @@ -0,0 +1,242 @@ +--- +library_name: transformers +tags: [] +--- + +# KO-REAson + +**KO-REAson** is a series of Korean-centric reasoning language models developed in collaboration with [OneLineAI](https://onelineai.com/), [KISTI-KONI](https://huggingface.co/KISTI-KONI), [HAE-RAE](https://huggingface.co/HAERAE-HUB) and ORACLE. + +We use the **Language-Mixed Chain-of-Thought (CoT)** approach, which allows the model to alternate between English and Korean during the “Think” stage of reasoning, preserving key Korean terms while leveraging English for logical scaffolding. + +Top-performing models of our series [KO-REAson-AX3_1-7B-0831 (KONI-7B-R-20250831)](https://huggingface.co/KISTI-KONI/KONI-7B-R-20250831) and [KO-REAson-7B-Q2_5-0831](https://huggingface.co/KoReason/KO-REASon-7B-Q2_5-0831) show performance comparable to models trained on closed-source datasets such as Exaone-Deep-7.8B. + + +

+ Model Comparison +
+ + Left: Average performance (Held-out-Ko) of open models trained on closed or open data; + our models are highlighted in green. + +

+ +## Model Details + +The **KO-REAson-0831** family comes in six variants based on the base model used. + +| Model (link) | Base | Notes | +| -------------------------------------------------------------------------------------------- | -------------------- | --------------------------- | +| [KO-REAson-L3_1-8B-0831](https://huggingface.co/KoReason/KO-REASon-L3_1-8B-0831) | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) | `L3_1` → Llama-3.1-8B | +| [KO-REAson-KL3_1-8B-0831](https://huggingface.co/KOREAson/KO-REAson-KL3_1-8B-0831) | [Koni-Llama-3.1-8B](https://huggingface.co/KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024) | `KL3_1` → Koni-Llama-3.1-8B; also called [KONI-Llama3.1-8B-R-20250831](https://huggingface.co/KISTI-KONI/KONI-Llama3.1-8B-R-20250831) | +| [KO-REAson-G3-4B-0831](https://huggingface.co/KoReason/KO-REASon-G3-4B-0831) | [Gemma-3 4B](https://huggingface.co/google/gemma-3-4b-it) | `G3` → Gemma-3-4B | +| [KO-REAson-AX3_1-7B-0831](https://huggingface.co/KOREAson/KO-REAson-7B-AX3_1-0831) | [A.X.-3.1-Light (≈7B)](https://huggingface.co/skt/A.X-3.1-Light) | `AX3_1` → A.X.-3.1-Light; also called [KONI-7B-R-20250831](https://huggingface.co/KISTI-KONI/KONI-7B-R-20250831) | +| [KO-REAson-K2505_8B-0831](https://huggingface.co/KoReason/KO-REASon-K2505_8B-0831) | [Kanana-2505 (8B)](https://huggingface.co/kakaocorp/kanana-1.5-8b-instruct-2505) | `K2505` → Kanana-2505 | +| [KO-REAson-7B-Q2_5-0831](https://huggingface.co/KoReason/KO-REASon-7B-Q2_5-0831) | [Qwen-2.5 (7B)](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | `Q2_5` → Qwen-2.5 | + + + +# Performance + +**Evaluation Datasets** + +The model's performance was evaluated across a total of 11 benchmarks, and the evaluation suite is divided into two parts: (You can check these benchmarks in [HAERAE-HUB/KoSimpleEval](https://huggingface.co/datasets/HAERAE-HUB/KoSimpleEval)) + +- **Held-in**: This set of benchmarks is used for routine monitoring of the model's performance during the training and ablation study phases. +- **Held-out**: This set is used only once to evaluate the final model after all training and ablations are complete. + +This separation is designed to prevent inadvertent overfitting to the benchmarks during the iterative training process and to provide a more accurate measure of the model's generalization capabilities. + +|**Category**|**Held-in**|**Held-out**| +|---|---|---| +|**General Knowledge**|KMMLU-Redux|KMMLU-HARD, KMMLU-Pro| +|**Reasoning**|MCLM|KSM, GPQA, AIME2024, AIME2025| +|**Korean-specific**|HAE-RAE Bench|CLIcK, KoBALT-700| + + +**Comparison with models trained on public datasets** + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Models# InstancesMethodologyHeld-Out (Ko)Held-Out (En)Total
KO-REASon-AX3_1-7B-0831(KONI-7B-R-20250831; Ours)260kSFT44.641.243.3
KO-REASon-7B-Q2_5-0831(Ours)260kSFT45.1038.7549.95
KO-REAson-KL3_1-8B-0831(KONI-Llama3.1-8B-R-20250831)260kSFT40.1330.5743.66
Open Recipe (En)
OpenThinker3-7B1.2MSFT33.655.541.8
s1.1-7B1kSFT35.623.431.1
Llama-3.1-Nemotron-Nano-8B-v1>3MSFT & RL27.044.133.4
Open Recipe (Ko)
Ko-R1-14B45kSFT43.746.344.7
Ko-R1-7B45kSFT27.336.130.6
LLaMa-3.1-Ko-Reasoning-8B63kSFT17.77.714.0
+ +**Held-out benchmark performance** + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelModel SizeGeneralReasoningKorean-SpecificAverage
(Held-out)		Average
(Held-out-Ko)
KMMLU-HARDKMMLU-ProKSMAIME 2024AIME 2025GPQACLIcKKoBALT-700
Llama-3.1-Nemotron-Nano-8B8.0321.4722.8947.0656.6743.3332.3234.549.2933.4527.05
Llama-3.1-Korean-Reasoning-8B-Instruct8.0314.9121.726.090.000.0023.2339.656.1413.9717.70
EXAONE-Deep-7.8B7.8240.9637.3570.8070.0063.3364.6554.2418.8652.5244.44
DeepSeek-R1-Distill-Qwen-7B7.620.0023.0056.0960.0040.0043.430.008.2928.8517.48
DeepSeek-R1-Distill-Llama-8B8.0323.2226.2629.9733.3320.0046.4639.0513.2928.9526.36
s1.1-7B7.6231.1637.7030.6016.6723.3330.3056.8421.8631.0635.63
OpenThinker3-7B7.6230.3126.2663.5966.6753.3346.4647.6910.1435.6330.60
Ko-R1-7B7.6128.4619.3151.6146.6733.3328.2832.484.7130.6127.31
KO-REAson-KL3_1-8B-0831(KONI-Llama3.1-8B-R-20250831)8.0344.6440.0837.9623.3330.0038.3856.3921.5730.5740.13
KO-REASon-AX3_1-7B-0831 (KONI-7B-R-20250831)7.2645.5738.1352.8053.3333.3336.8762.8623.4343.2944.56
KO-REASon-7B-Q2_5-08317.2646.8144.9348.1143.3330.0042.9360.6525.0042.7245.10
+ + +## Citation +``` +The paper will be released soon! +``` + + +## Contact + +For any questions contact us via the following email :) + +``` +spthsrbwls123@yonsei.ac.kr +``` + + +## Acknowlegments +This research was supported by the Korea Institute of Science and Technology Information (KISTI) (No.(KISTI) K25L1M1C1), aimed at developing KONI (KISTI Open Neural Intelligence), a large language model specialized in science and technology. \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1117055 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,47 @@ +{{ bos_token }} +{%- if messages[0]['role'] == 'system' -%} + {%- if messages[0]['content'] is string -%} + {%- set first_user_prefix = messages[0]['content'] + ' + +' -%} + {%- else -%} + {%- set first_user_prefix = messages[0]['content'][0]['text'] + ' + +' -%} + {%- endif -%} + {%- set loop_messages = messages[1:] -%} +{%- else -%} + {%- set first_user_prefix = "" -%} + {%- set loop_messages = messages -%} +{%- endif -%} +{%- for message in loop_messages -%} + {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%} + {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }} + {%- endif -%} + {%- if (message['role'] == 'assistant') -%} + {%- set role = "model" -%} + {%- else -%} + {%- set role = message['role'] -%} + {%- endif -%} + {{ '' + role + ' +' + (first_user_prefix if loop.first else "") }} + {%- if message['content'] is string -%} + {{ message['content'] | trim }} + {%- elif message['content'] is iterable -%} + {%- for item in message['content'] -%} + {%- if item['type'] == 'image' -%} + {{ '' }} + {%- elif item['type'] == 'text' -%} + {{ item['text'] | trim }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type") }} + {%- endif -%} + {{ ' +' }} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{'model +'}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..ce7a877 --- /dev/null +++ b/config.json @@ -0,0 +1,73 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 10240, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 8, + "num_hidden_layers": 34, + "num_key_value_heads": 4, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": { + "factor": 8.0, + "rope_type": "linear" + }, + "rope_theta": 1000000.0, + "sliding_window": 1024, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "vocab_size": 262208 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..26f49e3 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "attn_implementation": "flash_attention_2", + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 106 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "4.55.4" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..8658622 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd539f8629ad29ff4b5471b3b6c9e12c22e4c57e20505db155a4ab6ccf577be +size 4992144616 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..dc4b8e2 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b17a29729f0840dd1aa48c34a3c0a970db58415345ce45c81777bacb9dece09 +size 4928888200 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..f4b8241 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e41e9d487254987e25e46e9afff6f7fc7ce3ca4fb2ed199fa504a9bbb0e0b4 +size 4907914352 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..fdd6c5d --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c248c3a3aec80ccb90fe8b960b61ac935ab0aeda5df3a52528a4529e256ff74b +size 692156768 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..485e0c9 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,452 @@ +{ + "metadata": { + "total_parameters": 3880263168, + "total_size": 15521052672 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1a61932 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "boi_token": "", + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eoi_token": "", + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "image_token": "", + "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.json b/tokenizer.json new file mode 100644 index 0000000..29401f9 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795 +size 33384568 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..bc94927 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9eb07a8977365e218a4e3c61fafa8c5ffe284a8d03d8088402fb4ae13635e79 +size 1155410