commit 334ca5923996b704bd67b272c3df6161312a40da Author: ModelHub XC Date: Sun Apr 12 12:10:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: AdaptLLM/finance-LLM-13B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c406d93 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00006.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00006.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00003-of-00006.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00004-of-00006.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00005-of-00006.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00006-of-00006.bin filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ffed799 --- /dev/null +++ b/README.md @@ -0,0 +1,142 @@ +--- +language: +- en +datasets: +- Open-Orca/OpenOrca +- GAIR/lima +- WizardLM/WizardLM_evol_instruct_V2_196k +metrics: +- accuracy +pipeline_tag: text-generation +tags: +- finance +--- + +# Adapting LLMs to Domains via Continual Pre-Training (ICLR 2024) +This repo contains the domain-specific base model developed from **LLaMA-1-13B**, using the method in our paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530). + +We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**. + +### [2024/11/29] 🤗 Introduce the multimodal version of AdaptLLM at [AdaMLLM](https://huggingface.co/papers/2411.19930), for adapting MLLMs to domains 🤗 + +**************************** **Updates** **************************** +* 2024/11/29: Released [AdaMLLM](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains) for adapting MLLMs to domains +* 2024/9/20: Our [research paper for Instruction-Pretrain](https://huggingface.co/papers/2406.14491) has been accepted by EMNLP 2024 +* 2024/8/29: Updated [guidelines](https://huggingface.co/datasets/AdaptLLM/finance-tasks) on evaluating any 🤗Huggingface models on the domain-specific tasks +* 2024/6/22: Released the [benchmarking code](https://github.com/microsoft/LMOps/tree/main/adaptllm) +* 2024/6/21: Released the general version of AdaptLLM at [Instruction-Pretrain](https://huggingface.co/instruction-pretrain) +* 2024/4/2: Released the [raw data splits (train and test)](https://huggingface.co/datasets/AdaptLLM/ConvFinQA) of all the evaluation datasets +* 2024/1/16: Our [research paper for AdaptLLM](https://huggingface.co/papers/2309.09530) has been accepted by ICLR 2024 +* 2023/12/19: Released our [13B base models](https://huggingface.co/AdaptLLM/law-LLM-13B) developed from LLaMA-1-13B +* 2023/12/8: Released our [chat models](https://huggingface.co/AdaptLLM/law-chat) developed from LLaMA-2-Chat-7B +* 2023/9/18: Released our [paper](https://huggingface.co/papers/2309.09530), [code](https://github.com/microsoft/LMOps), [data](https://huggingface.co/datasets/AdaptLLM/law-tasks), and [base models](https://huggingface.co/AdaptLLM/law-LLM) developed from LLaMA-1-7B + +## 1. Domain-Specific Models +### LLaMA-1-7B +In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are: + +

+ +

+ +### LLaMA-1-13B +Moreover, we scale up our base model to LLaMA-1-13B to see if **our method is similarly effective for larger-scale models**, and the results are consistently positive too: [Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B), [Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B) and [Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B). + +### LLaMA-2-Chat +Our method is also effective for aligned models! LLaMA-2-Chat requires a [specific data format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), and our **reading comprehension can perfectly fit the data format** by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: [Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat), [Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat) and [Law-Chat](https://huggingface.co/AdaptLLM/law-chat). + +For example, to chat with the finance model: +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-LLM-13B") +tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-LLM-13B", use_fast=False) + +# Put your input here: +user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered +Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange +MMM Chicago Stock Exchange, Inc. +1.500% Notes due 2026 MMM26 New York Stock Exchange +1.750% Notes due 2030 MMM30 New York Stock Exchange +1.500% Notes due 2031 MMM31 New York Stock Exchange + +Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?''' + +# Simply use your input as the prompt for base models +prompt = user_input + +inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device) +outputs = model.generate(input_ids=inputs, max_length=2048)[0] + +answer_start = int(inputs.shape[-1]) +pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True) + +print(pred) +``` + +### LLaMA-3-8B (💡New!) +In our recent research on [Instruction-Pretrain](https://huggingface.co/papers/2406.14491), we developed a context-based instruction synthesizer to augment the raw corpora with instruction-response pairs, **enabling Llama3-8B to be comparable to or even outperform Llama3-70B**: [Finance-Llama3-8B](https://huggingface.co/instruction-pretrain/finance-Llama3-8B), [Biomedicine-Llama3-8B](https://huggingface.co/instruction-pretrain/medicine-Llama3-8B). + +## 2. Domain-Specific Tasks + +### Pre-templatized Testing Splits +To easily reproduce our prompting results, we have uploaded the filled-in zero/few-shot input instructions and output completions of the test each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks). + +Note: those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models. + +### Evaluating Any Huggingface LMs on Domain-Specific Tasks (💡New!) +You can use the following script to reproduce our results and evaluate any other Huggingface models on domain-specific tasks. Note that the script is NOT applicable to models that require specific prompt templates (e.g., Llama2-chat, Llama3-Instruct). + +1). **Set Up Dependencies** + ```bash + git clone https://github.com/microsoft/LMOps + cd LMOps/adaptllm + pip install -r requirements.txt + ``` + +2). **Evaluate the Model** + ```bash + # Select the domain from ['biomedicine', 'finance', 'law'] + DOMAIN='finance' + + # Specify any Huggingface model name (Not applicable to chat models) + MODEL='AdaptLLM/finance-LLM-13B' + + # Model parallelization: + # - Set MODEL_PARALLEL=False if the model fits on a single GPU. + # We observe that LMs smaller than 10B always meet this requirement. + # - Set MODEL_PARALLEL=True if the model is too large and encounters OOM on a single GPU. + MODEL_PARALLEL=True + + # Choose the number of GPUs from [1, 2, 4, 8] + N_GPU=2 + + # Whether to add a BOS token at the beginning of the prompt input: + # - Set to False for AdaptLLM. + # - Set to True for instruction-pretrain models. + # If unsure, we recommend setting it to False, as this is suitable for most LMs. + add_bos_token=False + + # Run the evaluation script + bash scripts/inference.sh ${DOMAIN} ${MODEL} ${add_bos_token} ${MODEL_PARALLEL} ${N_GPU} + ``` + +### Raw Datasets +We have also uploaded the raw training and testing splits, for facilitating fine-tuning or other usages: [ChemProt](https://huggingface.co/datasets/AdaptLLM/ChemProt), [RCT](https://huggingface.co/datasets/AdaptLLM/RCT), [ConvFinQA](https://huggingface.co/datasets/AdaptLLM/ConvFinQA), [FiQA_SA](https://huggingface.co/datasets/AdaptLLM/FiQA_SA), [Headline](https://huggingface.co/datasets/AdaptLLM/Headline), [NER](https://huggingface.co/datasets/AdaptLLM/NER), [FPB](https://huggingface.co/datasets/AdaptLLM/FPB) + +### Domain Knowledge Probing +Our pre-processed knowledge probing datasets are available at: [med_knowledge_prob](https://huggingface.co/datasets/AdaptLLM/med_knowledge_prob) and [law_knowledge_prob](https://huggingface.co/datasets/AdaptLLM/law_knowledge_prob) + + +## Citation +If you find our work helpful, please cite us: +```bibtex +@inproceedings{ +cheng2024adapting, +title={Adapting Large Language Models via Reading Comprehension}, +author={Daixuan Cheng and Shaohan Huang and Furu Wei}, +booktitle={The Twelfth International Conference on Learning Representations}, +year={2024}, +url={https://openreview.net/forum?id=y886UXPEZ0} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..1a63af9 --- /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": 32000, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.28.0.dev0", + "use_cache": true, + "vocab_size": 32001 +} 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..249dd1c --- /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": 32000, + "transformers_version": "4.28.0.dev0" +} diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..4751325 --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a822a3e95cb3e8165d568566c5f90808ecf932ff8a72646d8dcc02b11fd32da7 +size 9956547112 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..6b6d8ec --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dce0f60d985df43356d751a2e83dda5061eb1824908284a48b2bbfa633043fb +size 9940838856 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..aee736b --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2579dda9b6459e7cd1de0c022cbf642ed238bf318e0d1ba97a55c38d2028996a +size 9940839248 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..c97adaa --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c45c97ceb258b4db3ab151ae6a72c636b0edb6bd3ec97c94d6056029995249 +size 9867397864 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..71faa28 --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a3396c4250518acf25205d3b6b01a10701357e7d73edfaf7adfdcd9a7a5df5 +size 9867439048 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..dc23384 --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca23260b5c74167482613876be9291669bbc9f23f1926360eb9a434b459ce76d +size 2490492968 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a908ba4 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 52063508480 + }, + "weight_map": { + "lm_head.weight": "model-00006-of-00006.safetensors", + "model.embed_tokens.weight": "model-00001-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} \ No newline at end of file diff --git a/pytorch_model-00001-of-00006.bin b/pytorch_model-00001-of-00006.bin new file mode 100644 index 0000000..4e4cb40 --- /dev/null +++ b/pytorch_model-00001-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325037bc2a8ed5831073b865e39a15a15e63b81a004a750c33038d7506444081 +size 9956564363 diff --git a/pytorch_model-00002-of-00006.bin b/pytorch_model-00002-of-00006.bin new file mode 100644 index 0000000..b7ea4ae --- /dev/null +++ b/pytorch_model-00002-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354f6b798b0735cb8def3b0f9be37a5fcf4b551dc7877a32d7899fada634302b +size 9940856385 diff --git a/pytorch_model-00003-of-00006.bin b/pytorch_model-00003-of-00006.bin new file mode 100644 index 0000000..8c06b63 --- /dev/null +++ b/pytorch_model-00003-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f6e8f15f10affbd771e967ecd1505b1ba60e15cfd712c5cd52765c6d2131a6 +size 9940856943 diff --git a/pytorch_model-00004-of-00006.bin b/pytorch_model-00004-of-00006.bin new file mode 100644 index 0000000..d71ad5e --- /dev/null +++ b/pytorch_model-00004-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3d732c537925be75fb08551170231e509f57f7925ed728e7eb77a76362ccd1 +size 9867415289 diff --git a/pytorch_model-00005-of-00006.bin b/pytorch_model-00005-of-00006.bin new file mode 100644 index 0000000..a223c7d --- /dev/null +++ b/pytorch_model-00005-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634769714eb1862ab40880935b0f70a5969186d4c7910753adda966ed3db47a3 +size 9867456961 diff --git a/pytorch_model-00006-of-00006.bin b/pytorch_model-00006-of-00006.bin new file mode 100644 index 0000000..4c6475a --- /dev/null +++ b/pytorch_model-00006-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050379e31a2a25f5050ca1fb7fc5a3fa25fb3858d25521154f494d0287b8634f +size 2490496687 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..eb488e9 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 52063508480 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00006-of-00006.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.norm.weight": "pytorch_model-00006-of-00006.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..d245c4e --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa299a0662fc3bf7ada4d816b1cb9fdeb472e9edf6c2ffbc7f00e1b5ff5ff968 +size 499739 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6b0d946 --- /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": "", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}