commit 61353b348dd17f7a7e1b749384f5c02fcd9b4d9b Author: ModelHub XC Date: Wed Jun 24 10:02:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: AdaptLLM/law-LLM Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..470e58e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,101 @@ +*.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-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00009-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00010-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00011-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00012-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00013-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00014-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00015-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00016-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00017-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00018-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00019-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00020-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00021-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00022-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00023-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00024-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00025-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00026-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00027-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00028-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00029-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00030-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00031-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00032-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +model-00033-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00003-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00004-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00005-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00006-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00007-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00008-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00009-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00010-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00011-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00012-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00013-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00014-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00015-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00016-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00017-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00018-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00019-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00020-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00021-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00022-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00023-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00024-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00025-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00026-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00027-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00028-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00029-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00030-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00031-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00032-of-00033.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00033-of-00033.bin filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f064f56 --- /dev/null +++ b/README.md @@ -0,0 +1,142 @@ +--- +language: +- en +datasets: +- Open-Orca/OpenOrca +- GAIR/lima +- WizardLM/WizardLM_evol_instruct_V2_196k +- EleutherAI/pile +metrics: +- accuracy +pipeline_tag: text-generation +tags: +- legal +--- + +# Adapting LLMs to Domains via Continual Pre-Training (ICLR 2024) +This repo contains the domain-specific base model developed from **LLaMA-1-7B**, 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 law base model (🤗we highly recommend switching to the [chat model](https://huggingface.co/AdaptLLM/law-chat) for better response quality): +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("AdaptLLM/law-LLM") +tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/law-LLM", use_fast=False) + +# Put your input here: +user_input = '''Question: Which of the following is false about ex post facto laws? +Options: +- They make criminal an act that was innocent when committed. +- They prescribe greater punishment for an act than was prescribed when it was done. +- They increase the evidence required to convict a person than when the act was done. +- They alter criminal offenses or punishment in a substantially prejudicial manner for the purpose of punishing a person for some past activity. + +Please provide your choice first and then provide explanations if possible.''' + +# 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='law' + + # Specify any Huggingface model name (Not applicable to chat models) + MODEL='AdaptLLM/law-LLM' + + # 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=False + + # Choose the number of GPUs from [1, 2, 4, 8] + N_GPU=1 + + # 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/comparison.png b/comparison.png new file mode 100644 index 0000000..87b10f8 Binary files /dev/null and b/comparison.png differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..0ddcc20 --- /dev/null +++ b/config.json @@ -0,0 +1,21 @@ +{ + "architectures": [ + "LLaMAForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 1, + "hidden_act": "silu", + "hidden_size": 4096, + "intermediate_size": 11008, + "initializer_range": 0.02, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": 32000, + "rms_norm_eps": 1e-06, + "torch_dtype": "float16", + "transformers_version": "4.27.0.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..fcac46f --- /dev/null +++ b/generation_config.json @@ -0,0 +1 @@ +{"_from_model_config": true, "bos_token_id": 0, "eos_token_id": 1, "pad_token_id": 0, "transformers_version": "4.27.0.dev0"} \ No newline at end of file diff --git a/model-00001-of-00033.safetensors b/model-00001-of-00033.safetensors new file mode 100644 index 0000000..7ae35a3 --- /dev/null +++ b/model-00001-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60872ed9d159e4ae75ebd3ddfc2ce521eb9aa64bc7b274efb30b8ad50b75262f +size 809518344 diff --git a/model-00002-of-00033.safetensors b/model-00002-of-00033.safetensors new file mode 100644 index 0000000..a923369 --- /dev/null +++ b/model-00002-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304c1442e324e8d5036f37c125ec482bbd61116a2c568b80477b1905b446cc74 +size 809518344 diff --git a/model-00003-of-00033.safetensors b/model-00003-of-00033.safetensors new file mode 100644 index 0000000..43dd862 --- /dev/null +++ b/model-00003-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41495cb1ee3c318294db56e6e76fd6e4693e4e265ab8e7b5701681e18548af56 +size 809518344 diff --git a/model-00004-of-00033.safetensors b/model-00004-of-00033.safetensors new file mode 100644 index 0000000..7127eed --- /dev/null +++ b/model-00004-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6287124fd4c34a5f38c7e182d6c4b6d0ca8531e52a68609fa72d311773a6355b +size 809518344 diff --git a/model-00005-of-00033.safetensors b/model-00005-of-00033.safetensors new file mode 100644 index 0000000..ca6cec7 --- /dev/null +++ b/model-00005-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00184a65fa786b10da702afec4a9a20df75e9b5045f2c9da5af95552244e1eb5 +size 809518344 diff --git a/model-00006-of-00033.safetensors b/model-00006-of-00033.safetensors new file mode 100644 index 0000000..1b58949 --- /dev/null +++ b/model-00006-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c799a5735be1f80b64135b02741ad18214333770b6bebce5f892b740d1b713 +size 809518344 diff --git a/model-00007-of-00033.safetensors b/model-00007-of-00033.safetensors new file mode 100644 index 0000000..a8279fb --- /dev/null +++ b/model-00007-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614b15cc0f914d86d2ba6787981b3bb4fe665f962f0e08b29ffc1a6ecae9bd6e +size 809518344 diff --git a/model-00008-of-00033.safetensors b/model-00008-of-00033.safetensors new file mode 100644 index 0000000..b2a8bad --- /dev/null +++ b/model-00008-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33eabab03e02bfc1ac39691bf650261f4a9b6813e60ddacc449077aaf995a41c +size 809518344 diff --git a/model-00009-of-00033.safetensors b/model-00009-of-00033.safetensors new file mode 100644 index 0000000..f502288 --- /dev/null +++ b/model-00009-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0c4c2e4c5afeb981ec0dd0ef8281cfe1a9edf1098c6e375eddcdfbc951a022 +size 809518344 diff --git a/model-00010-of-00033.safetensors b/model-00010-of-00033.safetensors new file mode 100644 index 0000000..1a75540 --- /dev/null +++ b/model-00010-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b02bc8f67fae2173c043aafd51732f93124e1be0bebf82e68ba2d4e37d4d2d3 +size 809518344 diff --git a/model-00011-of-00033.safetensors b/model-00011-of-00033.safetensors new file mode 100644 index 0000000..c40471b --- /dev/null +++ b/model-00011-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4740f7835e506b6950b097f040d8346f1b7192a519bfc5309f2ff4596f5820ac +size 809518360 diff --git a/model-00012-of-00033.safetensors b/model-00012-of-00033.safetensors new file mode 100644 index 0000000..afcb94f --- /dev/null +++ b/model-00012-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d7b85b06764e31dcfdd464ca41f7ae3f8fa3ae242c2879a78a75060cd9f0c8 +size 809518360 diff --git a/model-00013-of-00033.safetensors b/model-00013-of-00033.safetensors new file mode 100644 index 0000000..d2e785c --- /dev/null +++ b/model-00013-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbc8162b6333c444a2ece66f379b260f3af23989a93acc1b13919c24eec26db +size 809518360 diff --git a/model-00014-of-00033.safetensors b/model-00014-of-00033.safetensors new file mode 100644 index 0000000..a194915 --- /dev/null +++ b/model-00014-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129b7a3699d4e2a3c91d1f006d01eef39c086f3959907fb665de7936cec6257b +size 809518360 diff --git a/model-00015-of-00033.safetensors b/model-00015-of-00033.safetensors new file mode 100644 index 0000000..bdb2219 --- /dev/null +++ b/model-00015-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55771c4ad545d3df908a93403bc3723c830a5d8b3aaae44788c4e9c2774b167 +size 809518360 diff --git a/model-00016-of-00033.safetensors b/model-00016-of-00033.safetensors new file mode 100644 index 0000000..8108fe8 --- /dev/null +++ b/model-00016-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00b73a9233e9b499b7ca744d5dd0666e28a801a743e116f1f09116d59bdb995 +size 809518360 diff --git a/model-00017-of-00033.safetensors b/model-00017-of-00033.safetensors new file mode 100644 index 0000000..b62bfdc --- /dev/null +++ b/model-00017-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66aac00a1da9893c3c637163c9c83b65dfef796246fb3caa6a99e52ea156a90 +size 809518360 diff --git a/model-00018-of-00033.safetensors b/model-00018-of-00033.safetensors new file mode 100644 index 0000000..caebdae --- /dev/null +++ b/model-00018-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c2d438a4cdbfcae4a90ee1fa2bed95461370527927fce8c116abc330be7c97 +size 809518360 diff --git a/model-00019-of-00033.safetensors b/model-00019-of-00033.safetensors new file mode 100644 index 0000000..b4ce01e --- /dev/null +++ b/model-00019-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b67d8b2e0d9abc67ceac8e8ef61e790d8aa427ea028021241675b771884cc38 +size 809518360 diff --git a/model-00020-of-00033.safetensors b/model-00020-of-00033.safetensors new file mode 100644 index 0000000..5c5924f --- /dev/null +++ b/model-00020-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09749961cd77bb776cdb1b11a8dcecb070f28aba39a3b2dd309de10ba8ed9a33 +size 809518360 diff --git a/model-00021-of-00033.safetensors b/model-00021-of-00033.safetensors new file mode 100644 index 0000000..867d51a --- /dev/null +++ b/model-00021-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afc4035835817438d33855d79269bff15dbc2cf86568d68d7b79ecbfb453bfb +size 809518360 diff --git a/model-00022-of-00033.safetensors b/model-00022-of-00033.safetensors new file mode 100644 index 0000000..e48b25d --- /dev/null +++ b/model-00022-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44bca87e5f800719a39e779e386f071118926ba295b84504f1547230c5d41d6 +size 809518360 diff --git a/model-00023-of-00033.safetensors b/model-00023-of-00033.safetensors new file mode 100644 index 0000000..75f9260 --- /dev/null +++ b/model-00023-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e33a2f6936acaa8cfa7f7c9f366665b00e4547f2289c614722294bf14377d15 +size 809518360 diff --git a/model-00024-of-00033.safetensors b/model-00024-of-00033.safetensors new file mode 100644 index 0000000..82d0025 --- /dev/null +++ b/model-00024-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ecb0dddcf23fd779d36806e200e8a752e68de5d698cc5800679afa2a541fbfd +size 809518360 diff --git a/model-00025-of-00033.safetensors b/model-00025-of-00033.safetensors new file mode 100644 index 0000000..5cd7081 --- /dev/null +++ b/model-00025-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03c4703ba8d771a30cfdac12920ad4f7ea67bf015be8a5ec45f2369e484bd41 +size 809518360 diff --git a/model-00026-of-00033.safetensors b/model-00026-of-00033.safetensors new file mode 100644 index 0000000..260a51d --- /dev/null +++ b/model-00026-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff91fc66d6c3e50d23e6110f60d82d846dbd428f88f1500e612545e40c576f7 +size 809518360 diff --git a/model-00027-of-00033.safetensors b/model-00027-of-00033.safetensors new file mode 100644 index 0000000..2e06635 --- /dev/null +++ b/model-00027-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2f5a64330c05a4651a15b8797794db56e454c89b31173a0b7d821524250f13 +size 809518360 diff --git a/model-00028-of-00033.safetensors b/model-00028-of-00033.safetensors new file mode 100644 index 0000000..59a441e --- /dev/null +++ b/model-00028-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdaa62bf4fa08686856e17797e417304db5d806dc9623627ab76b35a2492235 +size 809518360 diff --git a/model-00029-of-00033.safetensors b/model-00029-of-00033.safetensors new file mode 100644 index 0000000..224d899 --- /dev/null +++ b/model-00029-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0bcb04f381e4b1e5b21ac6fd7c86da005589bb98c7b48bc6bf72584065b8c84 +size 809518360 diff --git a/model-00030-of-00033.safetensors b/model-00030-of-00033.safetensors new file mode 100644 index 0000000..fd4a4f2 --- /dev/null +++ b/model-00030-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6eb54fe72016a630329142f1b6ece79cb111f36bacd7617733665721ea84da +size 809518360 diff --git a/model-00031-of-00033.safetensors b/model-00031-of-00033.safetensors new file mode 100644 index 0000000..2995125 --- /dev/null +++ b/model-00031-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f307b76ef41ec4ae56bd59bf24e9524c0cbb9addb50405881b643aa9123f308 +size 809518360 diff --git a/model-00032-of-00033.safetensors b/model-00032-of-00033.safetensors new file mode 100644 index 0000000..d7e9431 --- /dev/null +++ b/model-00032-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608e2cd2aace4944d9f9d52f0d397a9a336948398630506e78f5d10ccee98547 +size 809518360 diff --git a/model-00033-of-00033.safetensors b/model-00033-of-00033.safetensors new file mode 100644 index 0000000..1bc1f8b --- /dev/null +++ b/model-00033-of-00033.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1f269451964260be5acb2f589547582ab07024271d78f7f2e1ba6d8d98aafc +size 524312896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..dbaf333 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,330 @@ +{ + "weight_map": { + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00033.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00033.safetensors", + "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00033.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", + "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00002-of-00033.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00033.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00033.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", + "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00003-of-00033.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00033.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00033.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", + "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00004-of-00033.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00033.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00033.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", + "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00005-of-00033.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00006-of-00033.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00033.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", + "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00006-of-00033.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00007-of-00033.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00033.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", + "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00007-of-00033.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00008-of-00033.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00033.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", + "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00008-of-00033.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00009-of-00033.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00033.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", + "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00009-of-00033.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00010-of-00033.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00033.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", + "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00010-of-00033.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00011-of-00033.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00033.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", + "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00011-of-00033.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00012-of-00033.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00033.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", + "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00012-of-00033.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00013-of-00033.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00033.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", + "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00013-of-00033.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00014-of-00033.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00033.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", + "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00014-of-00033.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00015-of-00033.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00033.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", + "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00015-of-00033.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00016-of-00033.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00033.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", + "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00016-of-00033.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00017-of-00033.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00033.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", + "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00017-of-00033.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00018-of-00033.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00033.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", + "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00018-of-00033.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00019-of-00033.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00033.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", + "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00019-of-00033.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00020-of-00033.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00033.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", + "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00020-of-00033.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00021-of-00033.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00033.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", + "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00021-of-00033.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00022-of-00033.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00033.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", + "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00022-of-00033.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00023-of-00033.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00033.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", + "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00023-of-00033.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00024-of-00033.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00033.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", + "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00024-of-00033.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00025-of-00033.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00033.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", + "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00025-of-00033.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00026-of-00033.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00033.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", + "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00026-of-00033.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00027-of-00033.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00033.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", + "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00027-of-00033.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00028-of-00033.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00033.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", + "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00028-of-00033.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00029-of-00033.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00033.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", + "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00029-of-00033.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00030-of-00033.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00033.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", + "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00030-of-00033.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00031-of-00033.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00033.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", + "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00031-of-00033.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00032-of-00033.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00033.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", + "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00032-of-00033.safetensors", + "model.embed_tokens.weight": "model-00033-of-00033.safetensors", + "model.norm.weight": "model-00033-of-00033.safetensors", + "lm_head.weight": "model-00033-of-00033.safetensors" + }, + "metadata": { + "total_size": 13476835328 + } +} \ No newline at end of file diff --git a/pytorch_model-00001-of-00033.bin b/pytorch_model-00001-of-00033.bin new file mode 100644 index 0000000..eecd754 --- /dev/null +++ b/pytorch_model-00001-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f622c2399de6a2102b6fb6412326331ffd3ebe3a392692dc549db6b3e08a2df0 +size 809520963 diff --git a/pytorch_model-00002-of-00033.bin b/pytorch_model-00002-of-00033.bin new file mode 100644 index 0000000..7f83fee --- /dev/null +++ b/pytorch_model-00002-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a70e341ed0a7bc4eb00fd1f3c4019d6c9c4f459b02b599e9cdf434bf708bb10 +size 809520963 diff --git a/pytorch_model-00003-of-00033.bin b/pytorch_model-00003-of-00033.bin new file mode 100644 index 0000000..982d60c --- /dev/null +++ b/pytorch_model-00003-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdc4a22448fb4285a69dad41f3d572f7f302f95d047bec80afae7a48440312a +size 809520963 diff --git a/pytorch_model-00004-of-00033.bin b/pytorch_model-00004-of-00033.bin new file mode 100644 index 0000000..910f9c8 --- /dev/null +++ b/pytorch_model-00004-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005969658feaaab13050844bb297556536942fcfce619b923afdb2e729218609 +size 809520963 diff --git a/pytorch_model-00005-of-00033.bin b/pytorch_model-00005-of-00033.bin new file mode 100644 index 0000000..29ecc4f --- /dev/null +++ b/pytorch_model-00005-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e4ed5aad4c73303094fd2fc542a22b1c5bc447456c45e6d19c191983a68055 +size 809520963 diff --git a/pytorch_model-00006-of-00033.bin b/pytorch_model-00006-of-00033.bin new file mode 100644 index 0000000..ab02f9b --- /dev/null +++ b/pytorch_model-00006-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2147e47e821c01e1234481c6d3f9085200713c5d3a2776b87f0019f039956677 +size 809520963 diff --git a/pytorch_model-00007-of-00033.bin b/pytorch_model-00007-of-00033.bin new file mode 100644 index 0000000..5be03c0 --- /dev/null +++ b/pytorch_model-00007-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18626ae8d2d2bff6ad2096614d93ebf3ba3cb2aefa084c7db266d660d98d6d68 +size 809520963 diff --git a/pytorch_model-00008-of-00033.bin b/pytorch_model-00008-of-00033.bin new file mode 100644 index 0000000..7378250 --- /dev/null +++ b/pytorch_model-00008-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0ad2ddd370ce44b5fbaaff82cb451504396e0844a4ba2ce184046131df9564 +size 809520963 diff --git a/pytorch_model-00009-of-00033.bin b/pytorch_model-00009-of-00033.bin new file mode 100644 index 0000000..b8008a7 --- /dev/null +++ b/pytorch_model-00009-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a2263f5571330ec1c82ff56f5f586cc316b6da6c7b02cd78e77b0d6b0eaee6 +size 809520963 diff --git a/pytorch_model-00010-of-00033.bin b/pytorch_model-00010-of-00033.bin new file mode 100644 index 0000000..26ae77a --- /dev/null +++ b/pytorch_model-00010-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999d226e42bab664f61470ef442b8f37d8517ca1f62299393c82e55e1f6c8db7 +size 809520963 diff --git a/pytorch_model-00011-of-00033.bin b/pytorch_model-00011-of-00033.bin new file mode 100644 index 0000000..274efd6 --- /dev/null +++ b/pytorch_model-00011-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28284822a0345c267ad240fedc3c6aa166e2cc2a45a8c107751f947cff8acb4d +size 809520963 diff --git a/pytorch_model-00012-of-00033.bin b/pytorch_model-00012-of-00033.bin new file mode 100644 index 0000000..dd3ac77 --- /dev/null +++ b/pytorch_model-00012-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc4404ec4168db5adc55dcf4e61bd43f2c6d834e270e1de79846d60f93f5150 +size 809520963 diff --git a/pytorch_model-00013-of-00033.bin b/pytorch_model-00013-of-00033.bin new file mode 100644 index 0000000..b054602 --- /dev/null +++ b/pytorch_model-00013-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58caed7f0aa4a12dab78b5fda83e5eaf635670abd5d11591d7dd372aa8c30d3f +size 809520963 diff --git a/pytorch_model-00014-of-00033.bin b/pytorch_model-00014-of-00033.bin new file mode 100644 index 0000000..69c5815 --- /dev/null +++ b/pytorch_model-00014-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af78f4f6ae5c4a934eee05de2b34e69ba90d7f72c631c307762132df4f29ccd +size 809520963 diff --git a/pytorch_model-00015-of-00033.bin b/pytorch_model-00015-of-00033.bin new file mode 100644 index 0000000..64466ae --- /dev/null +++ b/pytorch_model-00015-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337fcc046f8fe8db5917e18a4e646f23df4ac40900098f8e1d673099bc073e52 +size 809520963 diff --git a/pytorch_model-00016-of-00033.bin b/pytorch_model-00016-of-00033.bin new file mode 100644 index 0000000..55b0705 --- /dev/null +++ b/pytorch_model-00016-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbda4128747268c581352e7944a8d48008db4843ea613e6b22b14481fa37339 +size 809520963 diff --git a/pytorch_model-00017-of-00033.bin b/pytorch_model-00017-of-00033.bin new file mode 100644 index 0000000..b7fdce9 --- /dev/null +++ b/pytorch_model-00017-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b2684def140c14484ba3aae08894c2ebb6788181fa175037dc0e059df50ba9 +size 809520963 diff --git a/pytorch_model-00018-of-00033.bin b/pytorch_model-00018-of-00033.bin new file mode 100644 index 0000000..df70a76 --- /dev/null +++ b/pytorch_model-00018-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272c05c0bee082019abe54c1cb19b5c439ae1aa3cb250f3de8f44a84741494cc +size 809520963 diff --git a/pytorch_model-00019-of-00033.bin b/pytorch_model-00019-of-00033.bin new file mode 100644 index 0000000..8c09df3 --- /dev/null +++ b/pytorch_model-00019-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f003ffcaf49ad26fad590ac15db8b7408c864ad436c6a98bd6de9256559675 +size 809520963 diff --git a/pytorch_model-00020-of-00033.bin b/pytorch_model-00020-of-00033.bin new file mode 100644 index 0000000..0e674ed --- /dev/null +++ b/pytorch_model-00020-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0292f55eb1e64fb1e278a214d164ddb168a1cd917e06ce533b00ae30d434f9 +size 809520963 diff --git a/pytorch_model-00021-of-00033.bin b/pytorch_model-00021-of-00033.bin new file mode 100644 index 0000000..f9ae7c6 --- /dev/null +++ b/pytorch_model-00021-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a740bcb6c1fbcca4ed0fec9803e49ac3eeab82333d1263fcfd0ef30934576a7 +size 809520963 diff --git a/pytorch_model-00022-of-00033.bin b/pytorch_model-00022-of-00033.bin new file mode 100644 index 0000000..f8c5917 --- /dev/null +++ b/pytorch_model-00022-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae842ff87975caa06f20e3f89e9c3f65d80bca7f2006ec48158a71a56fe83921 +size 809520963 diff --git a/pytorch_model-00023-of-00033.bin b/pytorch_model-00023-of-00033.bin new file mode 100644 index 0000000..ccd817a --- /dev/null +++ b/pytorch_model-00023-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23ea35d0786dbfb257b39ab54853ff4a812d51de651483ed027fd1885539db5 +size 809520963 diff --git a/pytorch_model-00024-of-00033.bin b/pytorch_model-00024-of-00033.bin new file mode 100644 index 0000000..28f555d --- /dev/null +++ b/pytorch_model-00024-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658c98a62291c50676c44b9da4774ba07334ff5bb71a7d0904cbb914cb0c8bf0 +size 809520963 diff --git a/pytorch_model-00025-of-00033.bin b/pytorch_model-00025-of-00033.bin new file mode 100644 index 0000000..51e7be6 --- /dev/null +++ b/pytorch_model-00025-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f16e1ee74e4ef3600737ddd1e1955c02221d51519200ddec8bbe25c944fd733 +size 809520963 diff --git a/pytorch_model-00026-of-00033.bin b/pytorch_model-00026-of-00033.bin new file mode 100644 index 0000000..cd74fc7 --- /dev/null +++ b/pytorch_model-00026-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d972ba0620cbe7f635a2fd6909c781ae09efd275139d17c92d4b338b728585 +size 809520963 diff --git a/pytorch_model-00027-of-00033.bin b/pytorch_model-00027-of-00033.bin new file mode 100644 index 0000000..ddfd8bd --- /dev/null +++ b/pytorch_model-00027-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1e6acd611c3aa95a81572c9334d8c11ad170abe1aabf5bd1b8429d19c386d9 +size 809520963 diff --git a/pytorch_model-00028-of-00033.bin b/pytorch_model-00028-of-00033.bin new file mode 100644 index 0000000..c6534e4 --- /dev/null +++ b/pytorch_model-00028-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d97720e2b553497e4dc19cbee8750819821ceae6adfedc6944f61399eebb5be +size 809520963 diff --git a/pytorch_model-00029-of-00033.bin b/pytorch_model-00029-of-00033.bin new file mode 100644 index 0000000..2ca0f76 --- /dev/null +++ b/pytorch_model-00029-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557a02a781c3e525d4f9b8fc21f93c6c9ffbf5fd8277465c3dc55c09cf006693 +size 809520963 diff --git a/pytorch_model-00030-of-00033.bin b/pytorch_model-00030-of-00033.bin new file mode 100644 index 0000000..c7e53dd --- /dev/null +++ b/pytorch_model-00030-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed9e1e173f43fe5c44988a7041229de8fdaae9db0a1a6f34951999b278b7823 +size 809520963 diff --git a/pytorch_model-00031-of-00033.bin b/pytorch_model-00031-of-00033.bin new file mode 100644 index 0000000..e931727 --- /dev/null +++ b/pytorch_model-00031-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2334d0695389306a57bebedfcdb427510ae11aebd981e47ab26a4813dc6b4cb0 +size 809520963 diff --git a/pytorch_model-00032-of-00033.bin b/pytorch_model-00032-of-00033.bin new file mode 100644 index 0000000..7cde442 --- /dev/null +++ b/pytorch_model-00032-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4dea5097bb1f7098f0bcb995c317d24319d3a1c918c92bf4ece69148a7aab79 +size 809520963 diff --git a/pytorch_model-00033-of-00033.bin b/pytorch_model-00033-of-00033.bin new file mode 100644 index 0000000..b2767b6 --- /dev/null +++ b/pytorch_model-00033-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15c633883b2d2fca8b84ba56b3e71f0f54cbbef73bcb49cc84b5b69bc2a0e6d1 +size 524314060 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..8259feb --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1 @@ +{"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00033.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00033.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00033.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00033.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00033.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00033.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00033.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00033.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00033.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00033.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00006-of-00033.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00033.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00033.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00033.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00008-of-00033.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00033.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00009-of-00033.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00033.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00010-of-00033.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00033.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00011-of-00033.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00033.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00012-of-00033.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00033.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00013-of-00033.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00033.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00014-of-00033.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00033.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00015-of-00033.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00033.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00016-of-00033.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00033.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00017-of-00033.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00033.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00018-of-00033.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00033.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00019-of-00033.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00033.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00020-of-00033.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00033.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00021-of-00033.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00033.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00022-of-00033.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00033.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00023-of-00033.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00033.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00024-of-00033.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00033.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00025-of-00033.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00033.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00026-of-00033.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00033.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00027-of-00033.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00033.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00028-of-00033.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00033.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00029-of-00033.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00033.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00030-of-00033.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00033.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00031-of-00033.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00033.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00032-of-00033.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00033.bin", "model.embed_tokens.weight": "pytorch_model-00033-of-00033.bin", "model.norm.weight": "pytorch_model-00033-of-00033.bin", "lm_head.weight": "pytorch_model-00033-of-00033.bin"}, "metadata": {"total_size": 13476835328}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file 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..2eaa536 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,8 @@ +{ + "bos_token": "", + "eos_token": "", + "model_max_length": 2048, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "pad_token": "" +}