commit 9fe4c4eddbed72a6382d3848a84140a82815b623 Author: ModelHub XC Date: Wed May 6 04:20:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ConvexAI/Metabird-7B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4139e49 --- /dev/null +++ b/README.md @@ -0,0 +1,166 @@ +--- +license: apache-2.0 +tags: +- generated_from_trainer +base_model: leveldevai/TurdusBeagle-7B +model-index: +- name: Metabird-7B + results: [] +--- + + + + + +![Metabird](https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/Haraj8I91wCax4JjdYmaN.jpeg) + +# Metabird-7B + +
See axolotl config + +axolotl version: `0.3.0` +```yaml +base_model: leveldevai/TurdusBeagle-7B +model_type: MistralForCausalLM +tokenizer_type: LlamaTokenizer +is_mistral_derived_model: true + +load_in_8bit: false +load_in_4bit: false +strict: false + +datasets: + - path: shuyuej/metamath_gsm8k + type: + system_prompt: "" + field_instruction: question + field_output: answer + format: "[INST] {instruction} [/INST]" + no_input_format: "[INST] {instruction} [/INST]" + +dataset_prepared_path: +val_set_size: 0.05 +output_dir: ./out + +sequence_len: 8192 +sample_packing: true +pad_to_sequence_len: true +eval_sample_packing: false + +wandb_project: +wandb_entity: +wandb_watch: +wandb_name: +wandb_log_model: + +gradient_accumulation_steps: 4 +micro_batch_size: 2 +num_epochs: 1 +optimizer: adamw_bnb_8bit +lr_scheduler: cosine +learning_rate: 0.000005 + +train_on_inputs: false +group_by_length: false +bf16: true +fp16: false +tf32: false + +gradient_checkpointing: true +early_stopping_patience: +resume_from_checkpoint: +local_rank: +logging_steps: 1 +xformers_attention: +flash_attention: true + +warmup_steps: 10 +evals_per_epoch: 4 +eval_table_size: +eval_table_max_new_tokens: 128 +saves_per_epoch: 1 +debug: +deepspeed: +weight_decay: 0.0 +fsdp: +fsdp_config: +special_tokens: + bos_token: "" + eos_token: "" + unk_token: "" + +``` + +

+ +## Metabird + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) + +This model is a fine-tuned version of [leveldevai/TurdusBeagle-7B](https://huggingface.co/leveldevai/TurdusBeagle-7B) on the shuyuej/metamath_gsm8k dataset. +It achieves the following results on the evaluation set: + +- Loss: 0.4017 + +## Model description + +More information soon + +## Intended uses & limitations + +More information soon + +## Training and evaluation data + +More information soon + +## Training procedure + +More information soon + + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 2 +- eval_batch_size: 2 +- seed: 42 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 8 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 10 +- num_epochs: 1 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:-----:|:----:|:---------------:| +| 0.9074 | 0.05 | 1 | 0.9932 | +| 0.5012 | 0.26 | 5 | 0.4849 | +| 0.4204 | 0.53 | 10 | 0.4435 | +| 0.3748 | 0.79 | 15 | 0.4017 | + + +### Framework versions + +- Transformers 4.37.0.dev0 +- Pytorch 2.0.1+cu117 +- Datasets 2.16.1 +- Tokenizers 0.15.0 + +# [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_ConvexAI__Metabird-7B) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |71.03| +|AI2 Reasoning Challenge (25-Shot)|69.54| +|HellaSwag (10-Shot) |87.54| +|MMLU (5-Shot) |65.27| +|TruthfulQA (0-shot) |57.94| +|Winogrande (5-shot) |83.03| +|GSM8k (5-shot) |62.85| + diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e36863d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,4 @@ +{ + "<|im_end|>": 32000, + "<|im_start|>": 32001 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..3e02580 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "leveldevai/TurdusBeagle-7B", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0.dev0", + "use_cache": false, + "vocab_size": 32002 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..59cf3fd --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.37.0.dev0", + "use_cache": false +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..40285fa --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4f9caaa5e8eb053e44da1cbe1bb8aebd673b107792df945c9cdb1b3c32d683 +size 4775371488 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..644846c --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fecb6c5c90a390cef4cbe5b5871e2bf043c22defef612078c2a04bd6309c3ee +size 4982990072 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..29d45f7 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9fbc1373e4d34b911f8f908ef75b7634b7f8885a9107095d2db446d3e2b2ea +size 4982990088 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..4a9a629 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0dbac63151a307e23e8d2d9321824d28d840ce2b3eb639257c5d5d9689cc81 +size 3500275608 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ada2363 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 18241593344 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "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.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_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.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_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.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_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.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_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.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_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.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_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.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_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.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_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.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_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-00003-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-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_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-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-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.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-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.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_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.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_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.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_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.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_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.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_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.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_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.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_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-00004-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-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_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-00004-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-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.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_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-00004-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.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.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_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.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_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-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-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.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-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.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_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" + } +} \ No newline at end of file diff --git a/pytorch_model-00001-of-00004.bin b/pytorch_model-00001-of-00004.bin new file mode 100644 index 0000000..ded80fc --- /dev/null +++ b/pytorch_model-00001-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fd3fcd17a86e1fd9e7879bb36b1c04f7bb9172409426f24ab54e06a1eae2dbf +size 4775389585 diff --git a/pytorch_model-00002-of-00004.bin b/pytorch_model-00002-of-00004.bin new file mode 100644 index 0000000..71db75a --- /dev/null +++ b/pytorch_model-00002-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d348ce307e33e6f5d15442a6032dac75072a0a1c3dc54190a48615fb19aa579 +size 4983009101 diff --git a/pytorch_model-00003-of-00004.bin b/pytorch_model-00003-of-00004.bin new file mode 100644 index 0000000..944bc66 --- /dev/null +++ b/pytorch_model-00003-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd48d4c92a27ebc2ff39e76d11a7104a3918a241f7aef5c08cc791315936135d +size 4983009101 diff --git a/pytorch_model-00004-of-00004.bin b/pytorch_model-00004-of-00004.bin new file mode 100644 index 0000000..a7b694d --- /dev/null +++ b/pytorch_model-00004-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a60ae5949ee0fd8f356817f7fac25105428c9d6afdca2db33e0803129db6a2e +size 3500287671 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..87c288a --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 18241593344 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00004-of-00004.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.norm.weight": "pytorch_model-00004-of-00004.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "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": "", + "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..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5b97181 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,61 @@ +{ + "add_bos_token": true, + "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 + }, + "32000": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": "", + "use_default_system_prompt": true, + "use_fast": true +}