commit 8fdd35be358ce3df592c487de9eff471f2e5c57e Author: ModelHub XC Date: Mon Jun 1 13:55:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Open-Orca/OpenOrca Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..af289b9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow 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 + +*.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 +*.safetensors 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 + +tokenizer.model filter=lfs diff=lfs merge=lfs -text +pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/OO_Preview1_AGIEval.png b/OO_Preview1_AGIEval.png new file mode 100644 index 0000000..a0f3812 Binary files /dev/null and b/OO_Preview1_AGIEval.png differ diff --git a/OO_Preview1_BigBenchHard.png b/OO_Preview1_BigBenchHard.png new file mode 100644 index 0000000..bfc82d2 Binary files /dev/null and b/OO_Preview1_BigBenchHard.png differ diff --git a/OpenOrca Nomic Atlas.png b/OpenOrca Nomic Atlas.png new file mode 100644 index 0000000..7a7205b Binary files /dev/null and b/OpenOrca Nomic Atlas.png differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..71f10fb --- /dev/null +++ b/README.md @@ -0,0 +1,123 @@ +--- +license: mit +language: +- en +library_name: transformers +pipeline_tag: text-generation +datasets: +- Open-Orca/OpenOrca +--- + +

🐋 The First OpenOrca Model Preview! 🐋

+ +![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png "OpenOrca Logo") + +# OpenOrca-Preview1-13B + +We have used our own [OpenOrca dataset](https://huggingface.co/datasets/Open-Orca/OpenOrca) to fine-tune LLaMA-13B. +This dataset is our attempt to reproduce the dataset generated for Microsoft Research's [Orca Paper](https://arxiv.org/abs/2306.02707). + +We have trained on less than 6% of our data, just to give a preview of what is possible while we further refine our dataset! +We trained a refined selection of 200k GPT-4 entries from OpenOrca. +We have filtered our GPT-4 augmentations to remove statements like, "As an AI language model..." and other responses which have been shown to harm model reasoning capabilities. Further details on our dataset curation practices will be forthcoming with our full model releases. + +This release highlights that even a small portion of our training data can produce state of the art results in this model class with training costs <$200 in total. + +Want to visualize our full (pre-filtering) dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2). + [Atlas Nomic Dataset Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2) + +We are in-process with training more models, so keep a look out on our org for releases coming soon with exciting partners. + +We will also give sneak-peak announcements on our Discord, which you can find here: + +https://AlignmentLab.ai + + +# Evaluation + +We have evaluated OpenOrca-Preview1-13B on hard reasoning tasks from BigBench-Hard and AGIEval as outlined in the Orca paper. + +Our average performance for BigBench-Hard: 0.3753 + +Average for AGIEval: 0.3638 + +In the Orca paper, they measured their score relative to Vicuna on these evals. +We've done the same and have found our score averages to ~60% of the total improvement that was shown in the Orca paper. + +So we got 60% of the improvement with 6% of the data! + +## BigBench-Hard Performance +![OpenOrca Preview1 BigBench-Hard Performance](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B/resolve/main/OO_Preview1_BigBenchHard.png "BigBench-Hard Performance") + +## AGIEval Performance +![OpenOrca Preview1 AGIEval Performance](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B/resolve/main/OO_Preview1_AGIEval.png "AGIEval Performance") + +We will report our results on [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Evals once we receive them. + + +# Dataset + +We used a small (6%, 200k) subset of our data from OpenOrca, which aims to reproduce the Orca Research Paper dataset. + +As this release is intended as a preview, please await our full releases for further details on the training data. + + +# Training + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) + +We trained with 8x A100-80G GPUs for 15 hours. Commodity cost was < $200. + +We trained for 4 epochs and selected a snapshot at 3 epochs for peak performance. + +Please await our full releases for further training details. + +# Prompting + +It uses the Alpaca format (see [FastChat implementation example](https://github.com/lm-sys/FastChat/blob/daa2b9abe20597ebf34dc5df164d450456610c74/fastchat/conversation.py#L198-L229)): +``` +### Instruction: + +### Response: +``` + +# Citation + +```bibtex +@software{OpenOrca_Preview1, + title = {OpenOrca_Preview1: A LLaMA-13B Model Fine-tuned on Small Portion of OpenOrcaV1 Dataset}, + author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B}, +} +``` +```bibtex +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +```bibtex +@misc{longpre2023flan, + title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, + author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts}, + year={2023}, + eprint={2301.13688}, + archivePrefix={arXiv}, + primaryClass={cs.AI} +} +``` +```bibtex +@software{touvron2023llama, + title={LLaMA: Open and Efficient Foundation Language Models}, + author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, + journal={arXiv preprint arXiv:2302.13971}, + year={2023} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..cfa72b4 --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "_name_or_path": "/home/sgugger/tmp/llama/llama-13b/", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 2048, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.28.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/configs/openorca.yml b/configs/openorca.yml new file mode 100644 index 0000000..3bbe307 --- /dev/null +++ b/configs/openorca.yml @@ -0,0 +1,67 @@ +base_model: huggyllama/llama-13b +base_model_config: huggyllama/llama-13b +model_type: LlamaForCausalLM +tokenizer_type: LlamaTokenizer +load_in_8bit: false +load_in_4bit: false +strict: false +push_dataset_to_hub: openaccess-ai-collective +hf_use_auth_token: true +datasets: + - path: Open-Orca/oo-gpt4-200k + type: alpaca_w_system.load_open_orca +dataset_prepared_path: last_run_prepared +val_set_size: 0.05 +adapter: +lora_model_dir: +sequence_len: 2048 +max_packed_sequence_len: +lora_r: +lora_alpha: +lora_dropout: +lora_target_modules: +lora_target_linear: +lora_fan_in_fan_out: +wandb_project: open-orca-13b +wandb_watch: +wandb_run_id: +wandb_log_model: +output_dir: ./open-orca-13b +gradient_accumulation_steps: 1 +micro_batch_size: 8 +num_epochs: 5 +optimizer: adamw_bnb_8bit +torchdistx_path: +lr_scheduler: cosine +learning_rate: 0.00005 +train_on_inputs: false +group_by_length: true +bf16: true +fp16: false +tf32: true +gradient_checkpointing: true +early_stopping_patience: +resume_from_checkpoint: +local_rank: +logging_steps: 1 +xformers_attention: true +flash_attention: +gptq_groupsize: +gptq_model_v1: +warmup_steps: 150 +eval_steps: 495 +save_steps: 2970 +debug: +deepspeed: +weight_decay: 0.03 +fsdp: + - full_shard + - auto_wrap +fsdp_config: + fsdp_offload_params: true + fsdp_state_dict_type: FULL_STATE_DICT + fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer +special_tokens: + bos_token: "" + eos_token: "" + unk_token: "" 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..55d7b5b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.0.dev0" +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..77bcf16 --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf75ebe44c0486660355f41c86049ed77b37444f73642b491a728ed7861471b +size 9948733550 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..a389bda --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e0df73c5382f56d202f715b2f5f76d99709bf106c78e987fa01d03799a175c +size 9904170208 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..c915ed1 --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3137d84aa8f5599c9c12b12515355ec0b090a7b6d93469070fcb5dbdc70af54 +size 6178986889 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..dd9a559 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 26031738880 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00003-of-00003.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.norm.weight": "pytorch_model-00003-of-00003.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..48d369b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 2048, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}