{"id":13653592,"url":"https://github.com/jianzhnie/LLamaTuner","last_synced_at":"2025-04-23T06:31:54.204Z","repository":{"id":169313222,"uuid":"645232426","full_name":"jianzhnie/LLamaTuner","owner":"jianzhnie","description":"Easy and Efficient Finetuning  LLMs. (Supported LLama, LLama2, LLama3, Qwen,  Baichuan, GLM , Falcon) 大模型高效量化训练+部署. ","archived":false,"fork":false,"pushed_at":"2025-01-24T08:33:52.000Z","size":1065,"stargazers_count":600,"open_issues_count":18,"forks_count":63,"subscribers_count":9,"default_branch":"main","last_synced_at":"2025-04-19T12:12:14.056Z","etag":null,"topics":["chatgpt","dpo","llama","llama3","mixtral","ppo","qlora","qwen","rlhf"],"latest_commit_sha":null,"homepage":"https://jianzhnie.github.io/llmtech/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jianzhnie.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-05-25T07:52:41.000Z","updated_at":"2025-04-18T12:01:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"240fe43d-92d2-43ad-9950-77f0fac312e2","html_url":"https://github.com/jianzhnie/LLamaTuner","commit_stats":{"total_commits":432,"total_committers":1,"mean_commits":432.0,"dds":0.0,"last_synced_commit":"698517da1c0c635d4960b2345422bd27e4ed1da6"},"previous_names":["jianzhnie/chinese-guanaco","jianzhnie/efficient-tuning-llms","jianzhnie/llamatuner"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FLLamaTuner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FLLamaTuner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FLLamaTuner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FLLamaTuner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jianzhnie","download_url":"https://codeload.github.com/jianzhnie/LLamaTuner/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250385194,"owners_count":21421874,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chatgpt","dpo","llama","llama3","mixtral","ppo","qlora","qwen","rlhf"],"created_at":"2024-08-02T02:01:13.274Z","updated_at":"2025-04-23T06:31:49.190Z","avatar_url":"https://github.com/jianzhnie.png","language":"Python","funding_links":[],"categories":["Others","A01_文本生成_文本对话"],"sub_categories":["Popular-LLM","大语言对话模型及数据"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/guanaco.svg\" width=\"300\"/\u003e\n\u003cdiv\u003e\u0026nbsp;\u003c/div\u003e\n\u003c/div\u003e\n\n![GitHub Repo stars](https://img.shields.io/github/stars/jianzhnie/Chinese-Guanaco?style=social)\n![GitHub Code License](https://img.shields.io/github/license/jianzhnie/Chinese-Guanaco)\n![GitHub last commit](https://img.shields.io/github/last-commit/jianzhnie/Chinese-Guanaco)\n![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)\n![issue resolution](https://img.shields.io/github/issues-closed-raw/jianzhnie/LLamaTuner)\n![open issues](https://img.shields.io/github/issues-raw/jianzhnie/LLamaTuner)\n[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/release/python-390/)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n\n\u003cdiv align=\"center\"\u003e\n\n👋🤗🤗👋 Join our [WeChat](assets/wechat.jpg).\n\n\u003c/div\u003e\n\n# Easy and Efficient Fine-tuning LLMs  --- 简单高效的大语言模型训练/部署\n\n\u003cdiv align=\"center\"\u003e\n\n[中文](README_zh.md) | English\n\n\u003c/div\u003e\n\n## Introduction\n\nLLamaTuner is an efficient, flexible and full-featured toolkit for fine-tuning LLM (Llama3, Phi3, Qwen, Mistral, ...)\n\n**Efficient**\n\n- Support LLM, VLM pre-training / fine-tuning on almost all GPUs. LLamaTuner is capable of fine-tuning 7B LLM on a single 8GB GPU, as well as multi-node fine-tuning of models exceeding 70B.\n- Automatically dispatch high-performance operators such as FlashAttention and Triton kernels to increase training throughput.\n- Compatible with [DeepSpeed](https://github.com/microsoft/DeepSpeed) 🚀, easily utilizing a variety of ZeRO optimization techniques.\n\n**Flexible**\n\n- Support various LLMs ([Llama 3](https://huggingface.co/meta-llama), [Mixtral](https://huggingface.co/mistralai), [Llama 2](https://huggingface.co/meta-llama), [ChatGLM](https://huggingface.co/THUDM), [Qwen](https://huggingface.co/Qwen), [Baichuan](https://huggingface.co/baichuan-inc), ...).\n- Support VLM ([LLaVA](https://github.com/haotian-liu/LLaVA)).\n- Well-designed data pipeline, accommodating datasets in any format, including but not limited to open-source and custom formats.\n- Support various training algorithms ([QLoRA](http://arxiv.org/abs/2305.14314), [LoRA](http://arxiv.org/abs/2106.09685), full-parameter fune-tune), allowing users to choose the most suitable solution for their requirements.\n\n**Full-featured**\n\n- Support continuous pre-training, instruction fine-tuning, and agent fine-tuning.\n- Support chatting with large models with pre-defined templates.\n\n## Table of Contents\n- [Easy and Efficient Fine-tuning LLMs  --- 简单高效的大语言模型训练/部署](#easy-and-efficient-fine-tuning-llms------简单高效的大语言模型训练部署)\n  - [Introduction](#introduction)\n  - [Table of Contents](#table-of-contents)\n  - [Supported Models](#supported-models)\n  - [Supported Training Approaches](#supported-training-approaches)\n  - [Supported Datasets](#supported-datasets)\n    - [Data Preprocessing](#data-preprocessing)\n  - [Model Zoo](#model-zoo)\n  - [Requirement](#requirement)\n    - [Hardware Requirement](#hardware-requirement)\n  - [Getting Started](#getting-started)\n    - [Clone the code](#clone-the-code)\n  - [Getting Started](#getting-started-1)\n    - [QLora int4 Finetune](#qlora-int4-finetune)\n  - [Known Issues and Limitations](#known-issues-and-limitations)\n  - [License](#license)\n  - [Acknowledgements](#acknowledgements)\n  - [Some lmm fine-tuning repos](#some-lmm-fine-tuning-repos)\n  - [Citation](#citation)\n\n\n## Supported Models\n\n| Model                                                | Model size                       | Default module  | Template  |\n| ---------------------------------------------------- | -------------------------------- | --------------- | --------- |\n| [Baichuan](https://huggingface.co/baichuan-inc)      | 7B/13B                           | W_pack          | baichuan  |\n| [Baichuan2](https://huggingface.co/baichuan-inc)     | 7B/13B                           | W_pack          | baichuan2 |\n| [BLOOM](https://huggingface.co/bigscience)           | 560M/1.1B/1.7B/3B/7.1B/176B      | query_key_value | -         |\n| [BLOOMZ](https://huggingface.co/bigscience)          | 560M/1.1B/1.7B/3B/7.1B/176B      | query_key_value | -         |\n| [ChatGLM3](https://huggingface.co/THUDM)             | 6B                               | query_key_value | chatglm3  |\n| [Command-R](https://huggingface.co/CohereForAI)      | 35B/104B                         | q_proj,v_proj   | cohere    |\n| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B                  | q_proj,v_proj   | deepseek  |\n| [Falcon](https://huggingface.co/tiiuae)              | 7B/11B/40B/180B                  | query_key_value | falcon    |\n| [Gemma/CodeGemma](https://huggingface.co/google)     | 2B/7B                            | q_proj,v_proj   | gemma     |\n| [InternLM2](https://huggingface.co/internlm)         | 7B/20B                           | wqkv            | intern2   |\n| [LLaMA](https://github.com/facebookresearch/llama)   | 7B/13B/33B/65B                   | q_proj,v_proj   | -         |\n| [LLaMA-2](https://huggingface.co/meta-llama)         | 7B/13B/70B                       | q_proj,v_proj   | llama2    |\n| [LLaMA-3](https://huggingface.co/meta-llama)         | 8B/70B                           | q_proj,v_proj   | llama3    |\n| [LLaVA-1.5](https://huggingface.co/llava-hf)         | 7B/13B                           | q_proj,v_proj   | vicuna    |\n| [Mistral/Mixtral](https://huggingface.co/mistralai)  | 7B/8x7B/8x22B                    | q_proj,v_proj   | mistral   |\n| [OLMo](https://huggingface.co/allenai)               | 1B/7B                            | q_proj,v_proj   | -         |\n| [PaliGemma](https://huggingface.co/google)           | 3B                               | q_proj,v_proj   | gemma     |\n| [Phi-1.5/2](https://huggingface.co/microsoft)        | 1.3B/2.7B                        | q_proj,v_proj   | -         |\n| [Phi-3](https://huggingface.co/microsoft)            | 3.8B                             | qkv_proj        | phi       |\n| [Qwen](https://huggingface.co/Qwen)                  | 1.8B/7B/14B/72B                  | c_attn          | qwen      |\n| [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen)    | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | q_proj,v_proj   | qwen      |\n| [StarCoder2](https://huggingface.co/bigcode)         | 3B/7B/15B                        | q_proj,v_proj   | -         |\n| [XVERSE](https://huggingface.co/xverse)              | 7B/13B/65B                       | q_proj,v_proj   | xverse    |\n| [Yi (1/1.5)](https://huggingface.co/01-ai)           | 6B/9B/34B                        | q_proj,v_proj   | yi        |\n| [Yi-VL](https://huggingface.co/01-ai)                | 6B/34B                           | q_proj,v_proj   | yi_vl     |\n| [Yuan](https://huggingface.co/IEITYuan)              | 2B/51B/102B                      | q_proj,v_proj   | yuan      |\n\n\n## Supported Training Approaches\n\n| Approach               | Full-tuning        | Freeze-tuning      | LoRA               | QLoRA              |\n| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ |\n| Pre-Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n| Supervised Fine-Tuning | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n| Reward Modeling        | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n| PPO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n| DPO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n| KTO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n| ORPO Training          | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n\n## Supported Datasets\n\nAs of now, we support the following datasets, most of which are all available in the [Hugging Face datasets library](https://huggingface.co/datasets/).\n\n\u003cdetails\u003e\u003csummary\u003eSupervised fine-tuning dataset\u003c/summary\u003e\n\n- [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca)\n- [Stanford Alpaca (Chinese)](https://github.com/ymcui/Chinese-LLaMA-Alpaca)\n- [Hello-SimpleAI/HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3)\n- [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)\n- [BELLE 1M (zh)](https://huggingface.co/datasets/BelleGroup/train_1M_CN)\n- [BELLE 0.5M (zh)](https://huggingface.co/datasets/BelleGroup/train_0.5M_CN)\n- [BELLE Dialogue 0.4M (zh)](https://huggingface.co/datasets/BelleGroup/generated_chat_0.4M)\n- [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)\n- [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)\n- [databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)\n- [mosaicml/dolly_hhrlhf](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf)\n- [GPT-4 Generated Data](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)\n- [Alpaca CoT](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)\n- [UltraChat](https://github.com/thunlp/UltraChat)\n- [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1)\n- [ShareGPT_Vicuna_unfiltered](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered)\n- [BIAI/OL-CC](https://data.baai.ac.cn/details/OL-CC)\n- [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)\n- [Evol-Instruct](https://huggingface.co/datasets/victor123/evol_instruct_70k)\n- [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)\n- [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)\n- [OpenHermes](https://huggingface.co/datasets/teknium/openhermes)\n\n\u003c/details\u003e\n\n\n\u003cdetails\u003e\u003csummary\u003ePreference datasets\u003c/summary\u003e\n\n- [DPO mixed (en\u0026zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)\n- [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)\n- [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)\n- [Open Assistant(en\u0026zh)](https://huggingface.co/datasets/OpenAssistant/oasst1)\n- [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)\n- [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)\n- [KTO mixed (en)](https://huggingface.co/datasets/argilla/kto-mix-15k)\n\u003c/details\u003e\n\n\nPlease refer to [data/README.md](data/README.md) to learn how to use these datasets.  If you want to explore more datasets, please refer to the [awesome-instruction-datasets](https://github.com/jianzhnie/awesome-instruction-datasets). Some datasets require confirmation before using them, so we recommend logging in with your Hugging Face account using these commands.\n\n```bash\npip install --upgrade huggingface_hub\nhuggingface-cli login\n```\n\n### Data Preprocessing\n\nWe provide a number of data preprocessing tools in the [data](./llamatuner/data) folder. These tools are intended to be a starting point for further research and development.\n\n- [data_utils.py](./llamatuner/data/data_utils.py) :  Data preprocessing and formatting\n- [sft_dataset.py](./llamatuner/data/sft_dataset.py) :  Supervised fine-tuning dataset class and collator\n- [conv_dataset.py](./llamatuner/data/conv_dataset.py) :  Conversation dataset class and collator\n\n## Model Zoo\n\nWe provide a number of models in the [Hugging Face model hub](https://huggingface.co/decapoda-research). These models are trained with QLoRA and can be used for inference and finetuning. We provide the following models:\n\n| Base Model                                                       | Adapter      | Instruct Datasets                                                                          | Train Script                                              | Log                                                               | Model on Huggingface                                                                |\n| ---------------------------------------------------------------- | ------------ | ------------------------------------------------------------------------------------------ | --------------------------------------------------------- | ----------------------------------------------------------------- | ----------------------------------------------------------------------------------- |\n| [llama-7b](https://huggingface.co/decapoda-research/llama-7b-hf) | FullFinetune | -                                                                                          | -                                                         | -                                                                 |                                                                                     |\n| [llama-7b](https://huggingface.co/decapoda-research/llama-7b-hf) | QLoRA        | [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) | [finetune_lamma7b](./scripts/finetune_llama_guanaco7b.sh) | [wandb log](https://wandb.ai/jianzhnie/huggingface/runs/1e2km7b1) | [GaussianTech/llama-7b-sft](https://huggingface.co/GaussianTech/llama-7b-sft)       |\n| [llama-7b](https://huggingface.co/decapoda-research/llama-7b-hf) | QLoRA        | [OL-CC](https://data.baai.ac.cn/details/OL-CC)                                             | [finetune_lamma7b](./scripts/finetune_llama_guanaco7b.sh) |                                                                   |                                                                                     |\n| [baichuan7b](https://huggingface.co/baichuan-inc/baichuan-7B)    | QLoRA        | [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) | [finetune_baichuan7b](./scripts/finetune_baichuan_7b.sh)  | [wandb log](https://wandb.ai/jianzhnie/huggingface/runs/41lq9joa) | [GaussianTech/baichuan-7b-sft](https://huggingface.co/GaussianTech/baichuan-7b-sft) |\n| [baichuan7b](https://huggingface.co/baichuan-inc/baichuan-7B)    | QLoRA        | [OL-CC](https://data.baai.ac.cn/details/OL-CC)                                             | [finetune_baichuan7b](./scripts/finetune_baichuan_7b.sh)  | [wandb log](https://wandb.ai/jianzhnie/huggingface/runs/1lw2bmvn) | -                                                                                   |\n\n## Requirement\n\n| Mandatory    | Minimum | Recommend |\n| ------------ | ------- | --------- |\n| python       | 3.8     | 3.10      |\n| torch        | 1.13.1  | 2.2.0     |\n| transformers | 4.37.2  | 4.41.0    |\n| datasets     | 2.14.3  | 2.19.1    |\n| accelerate   | 0.27.2  | 0.30.1    |\n| peft         | 0.9.0   | 0.11.1    |\n| trl          | 0.8.2   | 0.8.6     |\n\n| Optional     | Minimum | Recommend |\n| ------------ | ------- | --------- |\n| CUDA         | 11.6    | 12.2      |\n| deepspeed    | 0.10.0  | 0.14.0    |\n| bitsandbytes | 0.39.0  | 0.43.1    |\n| vllm         | 0.4.0   | 0.4.2     |\n| flash-attn   | 2.3.0   | 2.5.8     |\n\n### Hardware Requirement\n\n\\* *estimated*\n\n| Method            | Bits | 7B    | 13B   | 30B   | 70B    | 110B   | 8x7B  | 8x22B  |\n| ----------------- | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |\n| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 2000GB | 900GB | 2400GB |\n| Full              | 16   | 60GB  | 120GB | 300GB | 600GB  | 900GB  | 400GB | 1200GB |\n| Freeze            | 16   | 20GB  | 40GB  | 80GB  | 200GB  | 360GB  | 160GB | 400GB  |\n| LoRA/GaLore/BAdam | 16   | 16GB  | 32GB  | 64GB  | 160GB  | 240GB  | 120GB | 320GB  |\n| QLoRA             | 8    | 10GB  | 20GB  | 40GB  | 80GB   | 140GB  | 60GB  | 160GB  |\n| QLoRA             | 4    | 6GB   | 12GB  | 24GB  | 48GB   | 72GB   | 30GB  | 96GB   |\n| QLoRA             | 2    | 4GB   | 8GB   | 16GB  | 24GB   | 48GB   | 18GB  | 48GB   |\n\n\n## Getting Started\n\n### Clone the code\n\nClone this repository and navigate to the Efficient-Tuning-LLMs folder\n\n```bash\ngit clone https://github.com/jianzhnie/LLamaTuner.git\ncd LLamaTuner\n```\n\n## Getting Started\n\n| main function                    | Useage                                                                               | Scripts                                    |\n| -------------------------------- | ------------------------------------------------------------------------------------ | ------------------------------------------ |\n| [train.py](tools/train.py)           | Full finetune LLMs on  SFT datasets                                                  | [full_finetune](./scripts/full_finetune)   |\n| [train_lora.py](tools/train_lora.py) | Finetune LLMs by using Lora  (Low-Rank Adaptation of Large Language Models finetune) | [lora_finetune](./scripts/lora_finetune)   |\n| [train_qlora.py](tools/rain_qlora.py) | Finetune LLMs by using QLora (QLoRA: Efficient Finetuning of Quantized LLMs)         | [qlora_finetune](./scripts/qlora_finetune) |\n\n### QLora int4 Finetune\n\nThe `train_qlora.py` code is a starting point for finetuning and inference on various datasets.\nBasic command for finetuning a baseline model on the Alpaca dataset:\n\n```bash\npython train_qlora.py --model_name_or_path \u003cpath_or_name\u003e\n```\n\nFor models larger than 13B, we recommend adjusting the learning rate:\n\n```bash\npython train_qlora.py –learning_rate 0.0001 --model_name_or_path \u003cpath_or_name\u003e\n```\nTo find more scripts for finetuning and inference, please refer to the `scripts` folder.\n\n\n\n## Known Issues and Limitations\n\nHere a list of known issues and bugs. If your issue is not reported here, please open a new issue and describe the problem.\n\n1. 4-bit inference is slow. Currently, our 4-bit inference implementation is not yet integrated with the 4-bit matrix multiplication\n2. Resuming a LoRA training run with the Trainer currently runs on an error\n3. Currently, using `bnb_4bit_compute_type='fp16'` can lead to instabilities. For 7B LLaMA, only 80% of finetuning runs complete without error. We have solutions, but they are not integrated yet into bitsandbytes.\n4. Make sure that `tokenizer.bos_token_id = 1` to avoid generation issues.\n\n## License\n\n`LLamaTuner` is released under the Apache 2.0 license.\n\n## Acknowledgements\n\nWe thank the Huggingface team, in particular Younes Belkada, for their support integrating QLoRA with PEFT and transformers libraries.\n\nWe appreciate the work by many open-source contributors, especially:\n\n\n- [LLaMa](https://github.com/facebookresearch/llama/)\n- [Vicuna](https://github.com/lm-sys/FastChat/)\n- [xTuring](https://github.com/stochasticai/xTuring)\n- [Alpaca-LoRA](https://github.com/tloen/alpaca-lora/)\n- [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca/)\n- [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)\n- [Hugging Face](https://huggingface.co/)\n- [Peft](https://github.com/huggingface/peft.git)\n- [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl)\n- [deepspeed](https://www.deepspeed.ai/)\n- [Unsloth](https://github.com/unslothai/unsloth)\n- [qlora](https://github.com/artidoro/qlora)\n- [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)\n\n\n## Some lmm fine-tuning repos\n\n- https://github.com/QwenLM\n- https://github.com/InternLM\n- https://github.com/ymcui/Chinese-LLaMA-Alpaca-3\n- https://github.com/ymcui/Chinese-Mixtral\n- https://github.com/SmartFlowAI/EmoLLM\n- https://github.com/yangjianxin1/Firefly\n- https://github.com/LiuHC0428/LAW-GPT\n\n## Citation\n\nPlease cite the repo if you use the data or code in this repo.\n\n```bibtex\n@misc{Chinese-Guanaco,\n  author = {jianzhnie},\n  title = {LLamaTuner: Easy and Efficient Fine-tuning LLMs},\n  year = {2023},\n  publisher = {GitHub},\n  journal = {GitHub repository},\n  howpublished = {\\url{https://github.com/jianzhnie/LLamaTuner}},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjianzhnie%2FLLamaTuner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjianzhnie%2FLLamaTuner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjianzhnie%2FLLamaTuner/lists"}