llamafactory


Namellamafactory JSON
Version 0.9.0 PyPI version JSON
download
home_pagehttps://github.com/hiyouga/LLaMA-Factory
SummaryEasy-to-use LLM fine-tuning framework
upload_time2024-09-08 17:14:49
maintainerNone
docs_urlNone
authorhiyouga
requires_python>=3.8.0
licenseApache 2.0 License
keywords llama bloom falcon llm chatgpt transformer pytorch deep learning
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            ![# LLaMA Factory](assets/logo.png)

[![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Factory?style=social)](https://github.com/hiyouga/LLaMA-Factory/stargazers)
[![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Factory)](LICENSE)
[![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main)
[![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
[![Citation](https://img.shields.io/badge/citation-91-green)](#projects-using-llama-factory)
[![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)
[![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK)
[![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)
[![Open in DSW](https://gallery.pai-ml.com/assets/open-in-dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)
[![Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
[![Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)

[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)

👋 Join our [WeChat](assets/wechat.jpg) or [NPU user group](assets/wechat_npu.jpg).

\[ English | [中文](README_zh.md) \]

**Fine-tuning a large language model can be easy as...**

https://github.com/user-attachments/assets/7c96b465-9df7-45f4-8053-bf03e58386d3

Choose your path:

- **Colab**: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing
- **PAI-DSW**: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
- **Local machine**: Please refer to [usage](#getting-started)
- **Documentation (WIP)**: https://llamafactory.readthedocs.io/zh-cn/latest/

## Table of Contents

- [Features](#features)
- [Benchmark](#benchmark)
- [Changelog](#changelog)
- [Supported Models](#supported-models)
- [Supported Training Approaches](#supported-training-approaches)
- [Provided Datasets](#provided-datasets)
- [Requirement](#requirement)
- [Getting Started](#getting-started)
- [Projects using LLaMA Factory](#projects-using-llama-factory)
- [License](#license)
- [Citation](#citation)
- [Acknowledgement](#acknowledgement)

## Features

- **Various models**: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Qwen2-VL, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.
- **Integrated methods**: (Continuous) pre-training, (multimodal) supervised fine-tuning, reward modeling, PPO, DPO, KTO, ORPO, etc.
- **Scalable resources**: 16-bit full-tuning, freeze-tuning, LoRA and 2/3/4/5/6/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ.
- **Advanced algorithms**: [GaLore](https://github.com/jiaweizzhao/GaLore), [BAdam](https://github.com/Ledzy/BAdam), [Adam-mini](https://github.com/zyushun/Adam-mini), DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ, PiSSA and Agent tuning.
- **Practical tricks**: [FlashAttention-2](https://github.com/Dao-AILab/flash-attention), [Unsloth](https://github.com/unslothai/unsloth), [Liger Kernel](https://github.com/linkedin/Liger-Kernel), RoPE scaling, NEFTune and rsLoRA.
- **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, etc.
- **Faster inference**: OpenAI-style API, Gradio UI and CLI with vLLM worker.

## Benchmark

Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning), LLaMA Factory's LoRA tuning offers up to **3.7 times faster** training speed with a better Rouge score on the advertising text generation task. By leveraging 4-bit quantization technique, LLaMA Factory's QLoRA further improves the efficiency regarding the GPU memory.

![benchmark](assets/benchmark.svg)

<details><summary>Definitions</summary>

- **Training Speed**: the number of training samples processed per second during the training. (bs=4, cutoff_len=1024)
- **Rouge Score**: Rouge-2 score on the development set of the [advertising text generation](https://aclanthology.org/D19-1321.pdf) task. (bs=4, cutoff_len=1024)
- **GPU Memory**: Peak GPU memory usage in 4-bit quantized training. (bs=1, cutoff_len=1024)
- We adopt `pre_seq_len=128` for ChatGLM's P-Tuning and `lora_rank=32` for LLaMA Factory's LoRA tuning.

</details>

## Changelog

[24/08/30] We support fine-tuning the **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** models. Thank [@simonJJJ](https://github.com/simonJJJ)'s PR.

[24/08/27] We support **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**. Try `enable_liger_kernel: true` for efficient training.

[24/08/09] We support **[Adam-mini](https://github.com/zyushun/Adam-mini)** optimizer. See [examples](examples/README.md) for usage. Thank [@relic-yuexi](https://github.com/relic-yuexi)'s PR.

<details><summary>Full Changelog</summary>

[24/07/04] We support [contamination-free packed training](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing). Use `neat_packing: true` to activate it. Thank [@chuan298](https://github.com/chuan298)'s PR.

[24/06/16] We support **[PiSSA](https://arxiv.org/abs/2404.02948)** algorithm. See [examples](examples/README.md) for usage.

[24/06/07] We supported fine-tuning the **[Qwen2](https://qwenlm.github.io/blog/qwen2/)** and **[GLM-4](https://github.com/THUDM/GLM-4)** models.

[24/05/26] We supported **[SimPO](https://arxiv.org/abs/2405.14734)** algorithm for preference learning. See [examples](examples/README.md) for usage.

[24/05/20] We supported fine-tuning the **PaliGemma** series models. Note that the PaliGemma models are pre-trained models, you need to fine-tune them with `paligemma` template for chat completion.

[24/05/18] We supported **[KTO](https://arxiv.org/abs/2402.01306)** algorithm for preference learning. See [examples](examples/README.md) for usage.

[24/05/14] We supported training and inference on the Ascend NPU devices. Check [installation](#installation) section for details.

[24/04/26] We supported fine-tuning the **LLaVA-1.5** multimodal LLMs. See [examples](examples/README.md) for usage.

[24/04/22] We provided a **[Colab notebook](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)** for fine-tuning the Llama-3 model on a free T4 GPU. Two Llama-3-derived models fine-tuned using LLaMA Factory are available at Hugging Face, check [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) and [Llama3-Chinese](https://huggingface.co/zhichen/Llama3-Chinese) for details.

[24/04/21] We supported **[Mixture-of-Depths](https://arxiv.org/abs/2404.02258)** according to [AstraMindAI's implementation](https://github.com/astramind-ai/Mixture-of-depths). See [examples](examples/README.md) for usage.

[24/04/16] We supported **[BAdam](https://arxiv.org/abs/2404.02827)** optimizer. See [examples](examples/README.md) for usage.

[24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (Llama-2-7B-56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison).

[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See [examples](examples/README.md) for usage.

[24/03/21] Our paper "[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)" is available at arXiv!

[24/03/20] We supported **FSDP+QLoRA** that fine-tunes a 70B model on 2x24GB GPUs. See [examples](examples/README.md) for usage.

[24/03/13] We supported **[LoRA+](https://arxiv.org/abs/2402.12354)**. See [examples](examples/README.md) for usage.

[24/03/07] We supported **[GaLore](https://arxiv.org/abs/2403.03507)** optimizer. See [examples](examples/README.md) for usage.

[24/03/07] We integrated **[vLLM](https://github.com/vllm-project/vllm)** for faster and concurrent inference. Try `infer_backend: vllm` to enjoy **270%** inference speed.

[24/02/28] We supported weight-decomposed LoRA (**[DoRA](https://arxiv.org/abs/2402.09353)**). Try `use_dora: true` to activate DoRA training.

[24/02/15] We supported **block expansion** proposed by [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro). See [examples](examples/README.md) for usage.

[24/02/05] Qwen1.5 (Qwen2 beta version) series models are supported in LLaMA-Factory. Check this [blog post](https://qwenlm.github.io/blog/qwen1.5/) for details.

[24/01/18] We supported **agent tuning** for most models, equipping model with tool using abilities by fine-tuning with `dataset: glaive_toolcall_en`.

[23/12/23] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s implementation to boost LoRA tuning for the LLaMA, Mistral and Yi models. Try `use_unsloth: true` argument to activate unsloth patch. It achieves **170%** speed in our benchmark, check [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison) for details.

[23/12/12] We supported fine-tuning the latest MoE model **[Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)** in our framework. See hardware requirement [here](#hardware-requirement).

[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)** for Chinese mainland users. See [this tutorial](#download-from-modelscope-hub) for usage.

[23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `neftune_noise_alpha: 5` argument to activate NEFTune.

[23/09/27] We supported **$S^2$-Attn** proposed by [LongLoRA](https://github.com/dvlab-research/LongLoRA) for the LLaMA models. Try `shift_attn: true` argument to enable shift short attention.

[23/09/23] We integrated MMLU, C-Eval and CMMLU benchmarks in this repo. See [examples](examples/README.md) for usage.

[23/09/10] We supported **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**. Try `flash_attn: fa2` argument to enable FlashAttention-2 if you are using RTX4090, A100 or H100 GPUs.

[23/08/12] We supported **RoPE scaling** to extend the context length of the LLaMA models. Try `rope_scaling: linear` argument in training and `rope_scaling: dynamic` argument at inference to extrapolate the position embeddings.

[23/08/11] We supported **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [examples](examples/README.md) for usage.

[23/07/31] We supported **dataset streaming**. Try `streaming: true` and `max_steps: 10000` arguments to load your dataset in streaming mode.

[23/07/29] We released two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos ([LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/Baichuan-13B-sft)) for details.

[23/07/18] We developed an **all-in-one Web UI** for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.

[23/07/09] We released **[FastEdit](https://github.com/hiyouga/FastEdit)** ⚡🩹, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow [FastEdit](https://github.com/hiyouga/FastEdit) if you are interested.

[23/06/29] We provided a **reproducible example** of training a chat model using instruction-following datasets, see [Baichuan-7B-sft](https://huggingface.co/hiyouga/Baichuan-7B-sft) for details.

[23/06/22] We aligned the [demo API](src/api_demo.py) with the [OpenAI's](https://platform.openai.com/docs/api-reference/chat) format where you can insert the fine-tuned model in **arbitrary ChatGPT-based applications**.

[23/06/03] We supported quantized training and inference (aka **[QLoRA](https://github.com/artidoro/qlora)**). See [examples](examples/README.md) for usage.

</details>

## Supported Models

| Model                                                             | Model size                       | Template  |
| ----------------------------------------------------------------- | -------------------------------- | --------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |
| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3  |
| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere    |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek  |
| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon    |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma     |
| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4      |
| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2   |
| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -         |
| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2    |
| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama)            | 8B/70B                           | llama3    |
| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava     |
| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3  |
| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral   |
| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -         |
| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -         |
| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi       |
| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen      |
| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B                            | qwen2_vl  |
| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -         |
| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse    |
| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi        |
| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl     |
| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan      |

> [!NOTE]
> For the "base" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "instruct/chat" models.
>
> Remember to use the **SAME** template in training and inference.

Please refer to [constants.py](src/llamafactory/extras/constants.py) for a full list of models we supported.

You also can add a custom chat template to [template.py](src/llamafactory/data/template.py).

## Supported Training Approaches

| Approach               |     Full-tuning    |    Freeze-tuning   |       LoRA         |       QLoRA        |
| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ |
| Pre-Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| Supervised Fine-Tuning | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| Reward Modeling        | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| PPO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| DPO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| KTO Training           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| ORPO Training          | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| SimPO Training         | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |

> [!TIP]
> The implementation details of PPO can be found in [this blog](https://newfacade.github.io/notes-on-reinforcement-learning/17-ppo-trl.html).

## Provided Datasets

<details><summary>Pre-training datasets</summary>

- [Wiki Demo (en)](data/wiki_demo.txt)
- [RefinedWeb (en)](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)
- [RedPajama V2 (en)](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2)
- [Wikipedia (en)](https://huggingface.co/datasets/olm/olm-wikipedia-20221220)
- [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
- [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)
- [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)
- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)
- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
- [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)
- [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)

</details>

<details><summary>Supervised fine-tuning datasets</summary>

- [Identity (en&zh)](data/identity.json)
- [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
- [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3)
- [Alpaca GPT4 (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
- [Glaive Function Calling V2 (en&zh)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
- [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
- [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
- [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN)
- [BELLE 1M (zh)](https://huggingface.co/datasets/BelleGroup/train_1M_CN)
- [BELLE 0.5M (zh)](https://huggingface.co/datasets/BelleGroup/train_0.5M_CN)
- [BELLE Dialogue 0.4M (zh)](https://huggingface.co/datasets/BelleGroup/generated_chat_0.4M)
- [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)
- [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)
- [UltraChat (en)](https://github.com/thunlp/UltraChat)
- [OpenPlatypus (en)](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)
- [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
- [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
- [OpenOrca (en)](https://huggingface.co/datasets/Open-Orca/OpenOrca)
- [SlimOrca (en)](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- [MathInstruct (en)](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
- [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)
- [Wiki QA (en)](https://huggingface.co/datasets/wiki_qa)
- [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
- [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
- [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
- [deepctrl (en&zh)](https://www.modelscope.cn/datasets/deepctrl/deepctrl-sft-data)
- [Advertise Generating (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)
- [ShareGPT Hyperfiltered (en)](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k)
- [ShareGPT4 (en&zh)](https://huggingface.co/datasets/shibing624/sharegpt_gpt4)
- [UltraChat 200k (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)
- [AgentInstruct (en)](https://huggingface.co/datasets/THUDM/AgentInstruct)
- [LMSYS Chat 1M (en)](https://huggingface.co/datasets/lmsys/lmsys-chat-1m)
- [Evol Instruct V2 (en)](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)
- [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia)
- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
- [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
- [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
- [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)
- [OpenSchnabeltier (de)](https://huggingface.co/datasets/mayflowergmbh/openschnabeltier_de)
- [Evol Instruct (de)](https://huggingface.co/datasets/mayflowergmbh/evol-instruct_de)
- [Dolphin (de)](https://huggingface.co/datasets/mayflowergmbh/dolphin_de)
- [Booksum (de)](https://huggingface.co/datasets/mayflowergmbh/booksum_de)
- [Airoboros (de)](https://huggingface.co/datasets/mayflowergmbh/airoboros-3.0_de)
- [Ultrachat (de)](https://huggingface.co/datasets/mayflowergmbh/ultra-chat_de)

</details>

<details><summary>Preference datasets</summary>

- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
- [RLHF-V (en)](https://huggingface.co/datasets/openbmb/RLHF-V-Dataset)
- [VLFeedback (en)](https://huggingface.co/datasets/Zhihui/VLFeedback)
- [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
- [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
- [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
- [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
- [KTO mixed (en)](https://huggingface.co/datasets/argilla/kto-mix-15k)

</details>

Some datasets require confirmation before using them, so we recommend logging in with your Hugging Face account using these commands.

```bash
pip install --upgrade huggingface_hub
huggingface-cli login
```

## Requirement

| Mandatory    | Minimum | Recommend |
| ------------ | ------- | --------- |
| python       | 3.8     | 3.11      |
| torch        | 1.13.1  | 2.4.0     |
| transformers | 4.41.2  | 4.43.4    |
| datasets     | 2.16.0  | 2.20.0    |
| accelerate   | 0.30.1  | 0.32.0    |
| peft         | 0.11.1  | 0.12.0    |
| trl          | 0.8.6   | 0.9.6     |

| Optional     | Minimum | Recommend |
| ------------ | ------- | --------- |
| CUDA         | 11.6    | 12.2      |
| deepspeed    | 0.10.0  | 0.14.0    |
| bitsandbytes | 0.39.0  | 0.43.1    |
| vllm         | 0.4.3   | 0.5.0     |
| flash-attn   | 2.3.0   | 2.6.3     |

### Hardware Requirement

\* *estimated*

| Method            | Bits |   7B  |  13B  |  30B  |   70B  |  110B  |  8x7B |  8x22B |
| ----------------- | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 2000GB | 900GB | 2400GB |
| Full              |  16  |  60GB | 120GB | 300GB |  600GB |  900GB | 400GB | 1200GB |
| Freeze            |  16  |  20GB |  40GB |  80GB |  200GB |  360GB | 160GB |  400GB |
| LoRA/GaLore/BAdam |  16  |  16GB |  32GB |  64GB |  160GB |  240GB | 120GB |  320GB |
| QLoRA             |   8  |  10GB |  20GB |  40GB |   80GB |  140GB |  60GB |  160GB |
| QLoRA             |   4  |   6GB |  12GB |  24GB |   48GB |   72GB |  30GB |   96GB |
| QLoRA             |   2  |   4GB |   8GB |  16GB |   24GB |   48GB |  18GB |   48GB |

## Getting Started

### Installation

> [!IMPORTANT]
> Installation is mandatory.

```bash
git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics]"
```

Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, quality

> [!TIP]
> Use `pip install --no-deps -e .` to resolve package conflicts.

<details><summary>For Windows users</summary>

If you want to enable the quantized LoRA (QLoRA) on the Windows platform, you need to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.2, please select the appropriate [release version](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels) based on your CUDA version.

```bash
pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.2.post2-py3-none-win_amd64.whl
```

To enable FlashAttention-2 on the Windows platform, you need to install the precompiled `flash-attn` library, which supports CUDA 12.1 to 12.2. Please download the corresponding version from [flash-attention](https://github.com/bdashore3/flash-attention/releases) based on your requirements.

</details>

<details><summary>For Ascend NPU users</summary>

To install LLaMA Factory on Ascend NPU devices, please specify extra dependencies: `pip install -e ".[torch-npu,metrics]"`. Additionally, you need to install the **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**. Please follow the [installation tutorial](https://www.hiascend.com/document/detail/en/CANNCommunityEdition/600alphaX/softwareinstall/instg/atlasdeploy_03_0031.html) or use the following commands:

```bash
# replace the url according to your CANN version and devices
# install CANN Toolkit
wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run
bash Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run --install

# install CANN Kernels
wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run
bash Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run --install

# set env variables
source /usr/local/Ascend/ascend-toolkit/set_env.sh
```

| Requirement  | Minimum | Recommend   |
| ------------ | ------- | ----------- |
| CANN         | 8.0.RC1 | 8.0.RC1     |
| torch        | 2.1.0   | 2.1.0       |
| torch-npu    | 2.1.0   | 2.1.0.post3 |
| deepspeed    | 0.13.2  | 0.13.2      |

Remember to use `ASCEND_RT_VISIBLE_DEVICES` instead of `CUDA_VISIBLE_DEVICES` to specify the device to use.

If you cannot infer model on NPU devices, try setting `do_sample: false` in the configurations.

Download the pre-built Docker images: [32GB](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html) | [64GB](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)

</details>

### Data Preparation

Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope hub or load the dataset in local disk.

> [!NOTE]
> Please update `data/dataset_info.json` to use your custom dataset.

### Quickstart

Use the following 3 commands to run LoRA **fine-tuning**, **inference** and **merging** of the Llama3-8B-Instruct model, respectively.

```bash
llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
```

See [examples/README.md](examples/README.md) for advanced usage (including distributed training).

> [!TIP]
> Use `llamafactory-cli help` to show help information.

### Fine-Tuning with LLaMA Board GUI (powered by [Gradio](https://github.com/gradio-app/gradio))

```bash
llamafactory-cli webui
```

### Build Docker

For CUDA users:

```bash
cd docker/docker-cuda/
docker compose up -d
docker compose exec llamafactory bash
```

For Ascend NPU users:

```bash
cd docker/docker-npu/
docker compose up -d
docker compose exec llamafactory bash
```

For AMD ROCm users:

```bash
cd docker/docker-rocm/
docker compose up -d
docker compose exec llamafactory bash
```

<details><summary>Build without Docker Compose</summary>

For CUDA users:

```bash
docker build -f ./docker/docker-cuda/Dockerfile \
    --build-arg INSTALL_BNB=false \
    --build-arg INSTALL_VLLM=false \
    --build-arg INSTALL_DEEPSPEED=false \
    --build-arg INSTALL_FLASHATTN=false \
    --build-arg PIP_INDEX=https://pypi.org/simple \
    -t llamafactory:latest .

docker run -dit --gpus=all \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -p 7860:7860 \
    -p 8000:8000 \
    --shm-size 16G \
    --name llamafactory \
    llamafactory:latest

docker exec -it llamafactory bash
```

For Ascend NPU users:

```bash
# Choose docker image upon your environment
docker build -f ./docker/docker-npu/Dockerfile \
    --build-arg INSTALL_DEEPSPEED=false \
    --build-arg PIP_INDEX=https://pypi.org/simple \
    -t llamafactory:latest .

# Change `device` upon your resources
docker run -dit \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -v /usr/local/dcmi:/usr/local/dcmi \
    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
    -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
    -v /etc/ascend_install.info:/etc/ascend_install.info \
    -p 7860:7860 \
    -p 8000:8000 \
    --device /dev/davinci0 \
    --device /dev/davinci_manager \
    --device /dev/devmm_svm \
    --device /dev/hisi_hdc \
    --shm-size 16G \
    --name llamafactory \
    llamafactory:latest

docker exec -it llamafactory bash
```

For AMD ROCm users:

```bash
docker build -f ./docker/docker-rocm/Dockerfile \
    --build-arg INSTALL_BNB=false \
    --build-arg INSTALL_VLLM=false \
    --build-arg INSTALL_DEEPSPEED=false \
    --build-arg INSTALL_FLASHATTN=false \
    --build-arg PIP_INDEX=https://pypi.org/simple \
    -t llamafactory:latest .

docker run -dit \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -v ./saves:/app/saves \
    -p 7860:7860 \
    -p 8000:8000 \
    --device /dev/kfd \
    --device /dev/dri \
    --shm-size 16G \
    --name llamafactory \
    llamafactory:latest

docker exec -it llamafactory bash
```

</details>

<details><summary>Details about volume</summary>

- `hf_cache`: Utilize Hugging Face cache on the host machine. Reassignable if a cache already exists in a different directory.
- `ms_cache`: Similar to Hugging Face cache but for ModelScope users.
- `data`: Place datasets on this dir of the host machine so that they can be selected on LLaMA Board GUI.
- `output`: Set export dir to this location so that the merged result can be accessed directly on the host machine.

</details>

### Deploy with OpenAI-style API and vLLM

```bash
API_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml
```

> [!TIP]
> Visit [this page](https://platform.openai.com/docs/api-reference/chat/create) for API document.

### Download from ModelScope Hub

If you have trouble with downloading models and datasets from Hugging Face, you can use ModelScope.

```bash
export USE_MODELSCOPE_HUB=1 # `set USE_MODELSCOPE_HUB=1` for Windows
```

Train the model by specifying a model ID of the ModelScope Hub as the `model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `LLM-Research/Meta-Llama-3-8B-Instruct`.

### Use W&B Logger

To use [Weights & Biases](https://wandb.ai) for logging experimental results, you need to add the following arguments to yaml files.

```yaml
report_to: wandb
run_name: test_run # optional
```

Set `WANDB_API_KEY` to [your key](https://wandb.ai/authorize) when launching training tasks to log in with your W&B account.

## Projects using LLaMA Factory

If you have a project that should be incorporated, please contact via email or create a pull request.

<details><summary>Click to show</summary>

1. Wang et al. ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. 2023. [[arxiv]](https://arxiv.org/abs/2308.02223)
1. Yu et al. Open, Closed, or Small Language Models for Text Classification? 2023. [[arxiv]](https://arxiv.org/abs/2308.10092)
1. Wang et al. UbiPhysio: Support Daily Functioning, Fitness, and Rehabilitation with Action Understanding and Feedback in Natural Language. 2023. [[arxiv]](https://arxiv.org/abs/2308.10526)
1. Luceri et al. Leveraging Large Language Models to Detect Influence Campaigns in Social Media. 2023. [[arxiv]](https://arxiv.org/abs/2311.07816)
1. Zhang et al. Alleviating Hallucinations of Large Language Models through Induced Hallucinations. 2023. [[arxiv]](https://arxiv.org/abs/2312.15710)
1. Wang et al. Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs. KDD 2024. [[arxiv]](https://arxiv.org/abs/2401.04319)
1. Wang et al. CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning. ACL 2024. [[arxiv]](https://arxiv.org/abs/2401.07286)
1. Choi et al. FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2402.05904)
1. Zhang et al. AutoMathText: Autonomous Data Selection with Language Models for Mathematical Texts. 2024. [[arxiv]](https://arxiv.org/abs/2402.07625)
1. Lyu et al. KnowTuning: Knowledge-aware Fine-tuning for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.11176)
1. Yang et al. LaCo: Large Language Model Pruning via Layer Collaps. 2024. [[arxiv]](https://arxiv.org/abs/2402.11187)
1. Bhardwaj et al. Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic. 2024. [[arxiv]](https://arxiv.org/abs/2402.11746)
1. Yang et al. Enhancing Empathetic Response Generation by Augmenting LLMs with Small-scale Empathetic Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.11801)
1. Yi et al. Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding. ACL 2024 Findings. [[arxiv]](https://arxiv.org/abs/2402.11809)
1. Cao et al. Head-wise Shareable Attention for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.11819)
1. Zhang et al. Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages. 2024. [[arxiv]](https://arxiv.org/abs/2402.12204)
1. Kim et al. Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.14714)
1. Yu et al. KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models. ACL 2024. [[arxiv]](https://arxiv.org/abs/2402.15043)
1. Huang et al. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2403.02333)
1. Duan et al. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. 2024. [[arxiv]](https://arxiv.org/abs/2403.03419)
1. Xie and Schwertfeger. Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2403.08228)
1. Wu et al. Large Language Models are Parallel Multilingual Learners. 2024. [[arxiv]](https://arxiv.org/abs/2403.09073)
1. Zhang et al. EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling. 2024. [[arxiv]](https://arxiv.org/abs/2403.14541)
1. Weller et al. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2403.15246)
1. Hongbin Na. CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering. COLING 2024. [[arxiv]](https://arxiv.org/abs/2403.16008)
1. Zan et al. CodeS: Natural Language to Code Repository via Multi-Layer Sketch. 2024. [[arxiv]](https://arxiv.org/abs/2403.16443)
1. Liu et al. Extensive Self-Contrast Enables Feedback-Free Language Model Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2404.00604)
1. Luo et al. BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.02827)
1. Du et al. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2404.04167)
1. Ma et al. Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation. ICML 2024. [[arxiv]](https://arxiv.org/abs/2404.04316)
1. Liu et al. Dynamic Generation of Personalities with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.07084)
1. Shang et al. How Far Have We Gone in Stripped Binary Code Understanding Using Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.09836)
1. Huang et al. LLMTune: Accelerate Database Knob Tuning with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.11581)
1. Deng et al. Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction. 2024. [[arxiv]](https://arxiv.org/abs/2404.14215)
1. Acikgoz et al. Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare. 2024. [[arxiv]](https://arxiv.org/abs/2404.16621)
1. Zhang et al. Small Language Models Need Strong Verifiers to Self-Correct Reasoning. ACL 2024 Findings. [[arxiv]](https://arxiv.org/abs/2404.17140)
1. Zhou et al. FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering. NAACL 2024. [[arxiv]](https://arxiv.org/abs/2404.18585)
1. Xu et al. Large Language Models for Cyber Security: A Systematic Literature Review. 2024. [[arxiv]](https://arxiv.org/abs/2405.04760)
1. Dammu et al. "They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations. 2024. [[arxiv]](https://arxiv.org/abs/2405.05378)
1. Yi et al. A safety realignment framework via subspace-oriented model fusion for large language models. 2024. [[arxiv]](https://arxiv.org/abs/2405.09055)
1. Lou et al. SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling. 2024. [[arxiv]](https://arxiv.org/abs/2405.12739)
1. Zhang et al. Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners. 2024. [[arxiv]](https://arxiv.org/abs/2405.13816)
1. Zhang et al. TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2405.20215)
1. Zihong Chen. Sentence Segmentation and Sentence Punctuation Based on XunziALLM. 2024. [[paper]](https://aclanthology.org/2024.lt4hala-1.30)
1. Gao et al. The Best of Both Worlds: Toward an Honest and Helpful Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2406.00380)
1. Wang and Song. MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset. 2024. [[arxiv]](https://arxiv.org/abs/2406.02106)
1. Hu et al. Computational Limits of Low-Rank Adaptation (LoRA) for Transformer-Based Models. 2024. [[arxiv]](https://arxiv.org/abs/2406.03136)
1. Ge et al. Time Sensitive Knowledge Editing through Efficient Finetuning. ACL 2024. [[arxiv]](https://arxiv.org/abs/2406.04496)
1. Tan et al. Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions. 2024. [[arxiv]](https://arxiv.org/abs/2406.05688)
1. Song et al. Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters. 2024. [[arxiv]](https://arxiv.org/abs/2406.05955)
1. Gu et al. RWKV-CLIP: A Robust Vision-Language Representation Learner. 2024. [[arxiv]](https://arxiv.org/abs/2406.06973)
1. Chen et al. Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees. 2024. [[arxiv]](https://arxiv.org/abs/2406.07115)
1. Zhu et al. Are Large Language Models Good Statisticians?. 2024. [[arxiv]](https://arxiv.org/abs/2406.07815)
1. Li et al. Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning. 2024. [[arxiv]](https://arxiv.org/abs/2406.10099)
1. Ding et al. IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce. 2024. [[arxiv]](https://arxiv.org/abs/2406.10173)
1. He et al. COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities. 2024. [[arxiv]](https://arxiv.org/abs/2406.12074)
1. Lin et al. FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving. 2024. [[arxiv]](https://arxiv.org/abs/2406.14408)
1. Treutlein et al. Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data. 2024. [[arxiv]](https://arxiv.org/abs/2406.14546)
1. Feng et al. SS-Bench: A Benchmark for Social Story Generation and Evaluation. 2024. [[arxiv]](https://arxiv.org/abs/2406.15695)
1. Feng et al. Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement. 2024. [[arxiv]](https://arxiv.org/abs/2406.17233)
1. Liu et al. Large Language Models for Cuffless Blood Pressure Measurement From Wearable Biosignals. 2024. [[arxiv]](https://arxiv.org/abs/2406.18069)
1. Iyer et al. Exploring Very Low-Resource Translation with LLMs: The University of Edinburgh's Submission to AmericasNLP 2024 Translation Task. AmericasNLP 2024. [[paper]](https://aclanthology.org/2024.americasnlp-1.25)
1. Li et al. Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring. 2024. [[arxiv]](https://arxiv.org/abs/2406.19949)
1. Yang et al. Financial Knowledge Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2407.00365)
1. Lin et al. DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging. 2024. [[arxiv]](https://arxiv.org/abs/2407.01470)
1. Bako et al. Evaluating the Semantic Profiling Abilities of LLMs for Natural Language Utterances in Data Visualization. 2024. [[arxiv]](https://arxiv.org/abs/2407.06129)
1. Huang et al. RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization. 2024. [[arxiv]](https://arxiv.org/abs/2407.08044)
1. Jiang et al. LLM-Collaboration on Automatic Science Journalism for the General Audience. 2024. [[arxiv]](https://arxiv.org/abs/2407.09756)
1. Inouye et al. Applied Auto-tuning on LoRA Hyperparameters. 2024. [[paper]](https://scholarcommons.scu.edu/cseng_senior/272/)
1. Qi et al. Research on Tibetan Tourism Viewpoints information generation system based on LLM. 2024. [[arxiv]](https://arxiv.org/abs/2407.13561)
1. Xu et al. Course-Correction: Safety Alignment Using Synthetic Preferences. 2024. [[arxiv]](https://arxiv.org/abs/2407.16637)
1. Sun et al. LAMBDA: A Large Model Based Data Agent. 2024. [[arxiv]](https://arxiv.org/abs/2407.17535)
1. Zhu et al. CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare. 2024. [[arxiv]](https://arxiv.org/abs/2407.19705)
1. Yu et al. Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2408.00137)
1. Xie et al. The Power of Personalized Datasets: Advancing Chinese Composition Writing for Elementary School through Targeted Model Fine-Tuning. IALP 2024. [[paper]](https://www.asianlp.sg/conferences/ialp2024/proceedings/papers/IALP2024_P055.pdf)
1. Liu et al. Instruct-Code-Llama: Improving Capabilities of Language Model in Competition Level Code Generation by Online Judge Feedback. ICIC 2024. [[paper]](https://link.springer.com/chapter/10.1007/978-981-97-5669-8_11)
1. Wang et al. Cybernetic Sentinels: Unveiling the Impact of Safety Data Selection on Model Security in Supervised Fine-Tuning. ICIC 2024. [[paper]](https://link.springer.com/chapter/10.1007/978-981-97-5669-8_23)
1. Xia et al. Understanding the Performance and Estimating the Cost of LLM Fine-Tuning. 2024. [[arxiv]](https://arxiv.org/abs/2408.04693)
1. Zeng et al. Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2408.04168)
1. Xia et al. Using Pre-trained Language Model for Accurate ESG Prediction. FinNLP 2024. [[paper]](https://aclanthology.org/2024.finnlp-2.1/)
1. Liang et al. I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm. 2024. [[arxiv]](https://arxiv.org/abs/2408.08072)
1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: A large language model for Astronomy, based on ChatGLM2-6B and Qwen-14B.
1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: A large language model specialized in Chinese legal domain, based on Baichuan-13B, is capable of retrieving and reasoning on legal knowledge.
1. **[Sunsimiao](https://github.com/X-D-Lab/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B.
1. **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: A series of large language models for Chinese medical domain, based on LLaMA2-7B and Baichuan-13B.
1. **[MachineMindset](https://github.com/PKU-YuanGroup/Machine-Mindset/)**: A series of MBTI Personality large language models, capable of giving any LLM 16 different personality types based on different datasets and training methods.
1. **[Luminia-13B-v3](https://huggingface.co/Nekochu/Luminia-13B-v3)**: A large language model specialized in generate metadata for stable diffusion. [[🤗Demo]](https://huggingface.co/spaces/Nekochu/Luminia-13B_SD_Prompt)
1. **[Chinese-LLaVA-Med](https://github.com/BUAADreamer/Chinese-LLaVA-Med)**: A multimodal large language model specialized in Chinese medical domain, based on LLaVA-1.5-7B.
1. **[AutoRE](https://github.com/THUDM/AutoRE)**: A document-level relation extraction system based on large language models.
1. **[NVIDIA RTX AI Toolkit](https://github.com/NVIDIA/RTX-AI-Toolkit)**: SDKs for fine-tuning LLMs on Windows PC for NVIDIA RTX.
1. **[LazyLLM](https://github.com/LazyAGI/LazyLLM)**: An easy and lazy way for building multi-agent LLMs applications and supports model fine-tuning via LLaMA Factory.

</details>

## License

This repository is licensed under the [Apache-2.0 License](LICENSE).

Please follow the model licenses to use the corresponding model weights: [Baichuan 2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)

## Citation

If this work is helpful, please kindly cite as:

```bibtex
@inproceedings{zheng2024llamafactory,
  title={LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models},
  author={Yaowei Zheng and Richong Zhang and Junhao Zhang and Yanhan Ye and Zheyan Luo and Zhangchi Feng and Yongqiang Ma},
  booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  address={Bangkok, Thailand},
  publisher={Association for Computational Linguistics},
  year={2024},
  url={http://arxiv.org/abs/2403.13372}
}
```

## Acknowledgement

This repo benefits from [PEFT](https://github.com/huggingface/peft), [TRL](https://github.com/huggingface/trl), [QLoRA](https://github.com/artidoro/qlora) and [FastChat](https://github.com/lm-sys/FastChat). Thanks for their wonderful works.

## Star History

![Star History Chart](https://api.star-history.com/svg?repos=hiyouga/LLaMA-Factory&type=Date)

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/hiyouga/LLaMA-Factory",
    "name": "llamafactory",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.8.0",
    "maintainer_email": null,
    "keywords": "LLaMA, BLOOM, Falcon, LLM, ChatGPT, transformer, pytorch, deep learning",
    "author": "hiyouga",
    "author_email": "hiyouga@buaa.edu.cn",
    "download_url": "https://files.pythonhosted.org/packages/81/d1/6ba5f3b7f7b8fc492b5358116199ff4484e9ffbce3460fe40f315458237b/llamafactory-0.9.0.tar.gz",
    "platform": null,
    "description": "![# LLaMA Factory](assets/logo.png)\n\n[![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Factory?style=social)](https://github.com/hiyouga/LLaMA-Factory/stargazers)\n[![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Factory)](LICENSE)\n[![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main)\n[![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)\n[![Citation](https://img.shields.io/badge/citation-91-green)](#projects-using-llama-factory)\n[![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls)\n[![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK)\n[![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)\n[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)\n[![Open in DSW](https://gallery.pai-ml.com/assets/open-in-dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)\n[![Spaces](https://img.shields.io/badge/\ud83e\udd17-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)\n[![Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)\n\n[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)\n\n\ud83d\udc4b Join our [WeChat](assets/wechat.jpg) or [NPU user group](assets/wechat_npu.jpg).\n\n\\[ English | [\u4e2d\u6587](README_zh.md) \\]\n\n**Fine-tuning a large language model can be easy as...**\n\nhttps://github.com/user-attachments/assets/7c96b465-9df7-45f4-8053-bf03e58386d3\n\nChoose your path:\n\n- **Colab**: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing\n- **PAI-DSW**: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory\n- **Local machine**: Please refer to [usage](#getting-started)\n- **Documentation (WIP)**: https://llamafactory.readthedocs.io/zh-cn/latest/\n\n## Table of Contents\n\n- [Features](#features)\n- [Benchmark](#benchmark)\n- [Changelog](#changelog)\n- [Supported Models](#supported-models)\n- [Supported Training Approaches](#supported-training-approaches)\n- [Provided Datasets](#provided-datasets)\n- [Requirement](#requirement)\n- [Getting Started](#getting-started)\n- [Projects using LLaMA Factory](#projects-using-llama-factory)\n- [License](#license)\n- [Citation](#citation)\n- [Acknowledgement](#acknowledgement)\n\n## Features\n\n- **Various models**: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Qwen2-VL, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.\n- **Integrated methods**: (Continuous) pre-training, (multimodal) supervised fine-tuning, reward modeling, PPO, DPO, KTO, ORPO, etc.\n- **Scalable resources**: 16-bit full-tuning, freeze-tuning, LoRA and 2/3/4/5/6/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ.\n- **Advanced algorithms**: [GaLore](https://github.com/jiaweizzhao/GaLore), [BAdam](https://github.com/Ledzy/BAdam), [Adam-mini](https://github.com/zyushun/Adam-mini), DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ, PiSSA and Agent tuning.\n- **Practical tricks**: [FlashAttention-2](https://github.com/Dao-AILab/flash-attention), [Unsloth](https://github.com/unslothai/unsloth), [Liger Kernel](https://github.com/linkedin/Liger-Kernel), RoPE scaling, NEFTune and rsLoRA.\n- **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, etc.\n- **Faster inference**: OpenAI-style API, Gradio UI and CLI with vLLM worker.\n\n## Benchmark\n\nCompared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning), LLaMA Factory's LoRA tuning offers up to **3.7 times faster** training speed with a better Rouge score on the advertising text generation task. By leveraging 4-bit quantization technique, LLaMA Factory's QLoRA further improves the efficiency regarding the GPU memory.\n\n![benchmark](assets/benchmark.svg)\n\n<details><summary>Definitions</summary>\n\n- **Training Speed**: the number of training samples processed per second during the training. (bs=4, cutoff_len=1024)\n- **Rouge Score**: Rouge-2 score on the development set of the [advertising text generation](https://aclanthology.org/D19-1321.pdf) task. (bs=4, cutoff_len=1024)\n- **GPU Memory**: Peak GPU memory usage in 4-bit quantized training. (bs=1, cutoff_len=1024)\n- We adopt `pre_seq_len=128` for ChatGLM's P-Tuning and `lora_rank=32` for LLaMA Factory's LoRA tuning.\n\n</details>\n\n## Changelog\n\n[24/08/30] We support fine-tuning the **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** models. Thank [@simonJJJ](https://github.com/simonJJJ)'s PR.\n\n[24/08/27] We support **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**. Try `enable_liger_kernel: true` for efficient training.\n\n[24/08/09] We support **[Adam-mini](https://github.com/zyushun/Adam-mini)** optimizer. See [examples](examples/README.md) for usage. Thank [@relic-yuexi](https://github.com/relic-yuexi)'s PR.\n\n<details><summary>Full Changelog</summary>\n\n[24/07/04] We support [contamination-free packed training](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing). Use `neat_packing: true` to activate it. Thank [@chuan298](https://github.com/chuan298)'s PR.\n\n[24/06/16] We support **[PiSSA](https://arxiv.org/abs/2404.02948)** algorithm. See [examples](examples/README.md) for usage.\n\n[24/06/07] We supported fine-tuning the **[Qwen2](https://qwenlm.github.io/blog/qwen2/)** and **[GLM-4](https://github.com/THUDM/GLM-4)** models.\n\n[24/05/26] We supported **[SimPO](https://arxiv.org/abs/2405.14734)** algorithm for preference learning. See [examples](examples/README.md) for usage.\n\n[24/05/20] We supported fine-tuning the **PaliGemma** series models. Note that the PaliGemma models are pre-trained models, you need to fine-tune them with `paligemma` template for chat completion.\n\n[24/05/18] We supported **[KTO](https://arxiv.org/abs/2402.01306)** algorithm for preference learning. See [examples](examples/README.md) for usage.\n\n[24/05/14] We supported training and inference on the Ascend NPU devices. Check [installation](#installation) section for details.\n\n[24/04/26] We supported fine-tuning the **LLaVA-1.5** multimodal LLMs. See [examples](examples/README.md) for usage.\n\n[24/04/22] We provided a **[Colab notebook](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)** for fine-tuning the Llama-3 model on a free T4 GPU. Two Llama-3-derived models fine-tuned using LLaMA Factory are available at Hugging Face, check [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) and [Llama3-Chinese](https://huggingface.co/zhichen/Llama3-Chinese) for details.\n\n[24/04/21] We supported **[Mixture-of-Depths](https://arxiv.org/abs/2404.02258)** according to [AstraMindAI's implementation](https://github.com/astramind-ai/Mixture-of-depths). See [examples](examples/README.md) for usage.\n\n[24/04/16] We supported **[BAdam](https://arxiv.org/abs/2404.02827)** optimizer. See [examples](examples/README.md) for usage.\n\n[24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (Llama-2-7B-56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison).\n\n[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See [examples](examples/README.md) for usage.\n\n[24/03/21] Our paper \"[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)\" is available at arXiv!\n\n[24/03/20] We supported **FSDP+QLoRA** that fine-tunes a 70B model on 2x24GB GPUs. See [examples](examples/README.md) for usage.\n\n[24/03/13] We supported **[LoRA+](https://arxiv.org/abs/2402.12354)**. See [examples](examples/README.md) for usage.\n\n[24/03/07] We supported **[GaLore](https://arxiv.org/abs/2403.03507)** optimizer. See [examples](examples/README.md) for usage.\n\n[24/03/07] We integrated **[vLLM](https://github.com/vllm-project/vllm)** for faster and concurrent inference. Try `infer_backend: vllm` to enjoy **270%** inference speed.\n\n[24/02/28] We supported weight-decomposed LoRA (**[DoRA](https://arxiv.org/abs/2402.09353)**). Try `use_dora: true` to activate DoRA training.\n\n[24/02/15] We supported **block expansion** proposed by [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro). See [examples](examples/README.md) for usage.\n\n[24/02/05] Qwen1.5 (Qwen2 beta version) series models are supported in LLaMA-Factory. Check this [blog post](https://qwenlm.github.io/blog/qwen1.5/) for details.\n\n[24/01/18] We supported **agent tuning** for most models, equipping model with tool using abilities by fine-tuning with `dataset: glaive_toolcall_en`.\n\n[23/12/23] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s implementation to boost LoRA tuning for the LLaMA, Mistral and Yi models. Try `use_unsloth: true` argument to activate unsloth patch. It achieves **170%** speed in our benchmark, check [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison) for details.\n\n[23/12/12] We supported fine-tuning the latest MoE model **[Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)** in our framework. See hardware requirement [here](#hardware-requirement).\n\n[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)** for Chinese mainland users. See [this tutorial](#download-from-modelscope-hub) for usage.\n\n[23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `neftune_noise_alpha: 5` argument to activate NEFTune.\n\n[23/09/27] We supported **$S^2$-Attn** proposed by [LongLoRA](https://github.com/dvlab-research/LongLoRA) for the LLaMA models. Try `shift_attn: true` argument to enable shift short attention.\n\n[23/09/23] We integrated MMLU, C-Eval and CMMLU benchmarks in this repo. See [examples](examples/README.md) for usage.\n\n[23/09/10] We supported **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**. Try `flash_attn: fa2` argument to enable FlashAttention-2 if you are using RTX4090, A100 or H100 GPUs.\n\n[23/08/12] We supported **RoPE scaling** to extend the context length of the LLaMA models. Try `rope_scaling: linear` argument in training and `rope_scaling: dynamic` argument at inference to extrapolate the position embeddings.\n\n[23/08/11] We supported **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [examples](examples/README.md) for usage.\n\n[23/07/31] We supported **dataset streaming**. Try `streaming: true` and `max_steps: 10000` arguments to load your dataset in streaming mode.\n\n[23/07/29] We released two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos ([LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/Baichuan-13B-sft)) for details.\n\n[23/07/18] We developed an **all-in-one Web UI** for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development.\n\n[23/07/09] We released **[FastEdit](https://github.com/hiyouga/FastEdit)** \u26a1\ud83e\ude79, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow [FastEdit](https://github.com/hiyouga/FastEdit) if you are interested.\n\n[23/06/29] We provided a **reproducible example** of training a chat model using instruction-following datasets, see [Baichuan-7B-sft](https://huggingface.co/hiyouga/Baichuan-7B-sft) for details.\n\n[23/06/22] We aligned the [demo API](src/api_demo.py) with the [OpenAI's](https://platform.openai.com/docs/api-reference/chat) format where you can insert the fine-tuned model in **arbitrary ChatGPT-based applications**.\n\n[23/06/03] We supported quantized training and inference (aka **[QLoRA](https://github.com/artidoro/qlora)**). See [examples](examples/README.md) for usage.\n\n</details>\n\n## Supported Models\n\n| Model                                                             | Model size                       | Template  |\n| ----------------------------------------------------------------- | -------------------------------- | --------- |\n| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2 |\n| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |\n| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3  |\n| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere    |\n| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek  |\n| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon    |\n| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma     |\n| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4      |\n| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2   |\n| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -         |\n| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2    |\n| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama)            | 8B/70B                           | llama3    |\n| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava     |\n| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3  |\n| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral   |\n| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -         |\n| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma |\n| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -         |\n| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi       |\n| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen      |\n| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B                            | qwen2_vl  |\n| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -         |\n| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse    |\n| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi        |\n| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl     |\n| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan      |\n\n> [!NOTE]\n> For the \"base\" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the \"instruct/chat\" models.\n>\n> Remember to use the **SAME** template in training and inference.\n\nPlease refer to [constants.py](src/llamafactory/extras/constants.py) for a full list of models we supported.\n\nYou also can add a custom chat template to [template.py](src/llamafactory/data/template.py).\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| SimPO Training         | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |\n\n> [!TIP]\n> The implementation details of PPO can be found in [this blog](https://newfacade.github.io/notes-on-reinforcement-learning/17-ppo-trl.html).\n\n## Provided Datasets\n\n<details><summary>Pre-training datasets</summary>\n\n- [Wiki Demo (en)](data/wiki_demo.txt)\n- [RefinedWeb (en)](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)\n- [RedPajama V2 (en)](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2)\n- [Wikipedia (en)](https://huggingface.co/datasets/olm/olm-wikipedia-20221220)\n- [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)\n- [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)\n- [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)\n- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)\n- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)\n- [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)\n- [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)\n\n</details>\n\n<details><summary>Supervised fine-tuning datasets</summary>\n\n- [Identity (en&zh)](data/identity.json)\n- [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)\n- [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3)\n- [Alpaca GPT4 (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)\n- [Glaive Function Calling V2 (en&zh)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)\n- [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)\n- [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)\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- [UltraChat (en)](https://github.com/thunlp/UltraChat)\n- [OpenPlatypus (en)](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)\n- [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)\n- [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)\n- [OpenOrca (en)](https://huggingface.co/datasets/Open-Orca/OpenOrca)\n- [SlimOrca (en)](https://huggingface.co/datasets/Open-Orca/SlimOrca)\n- [MathInstruct (en)](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)\n- [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)\n- [Wiki QA (en)](https://huggingface.co/datasets/wiki_qa)\n- [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)\n- [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)\n- [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)\n- [deepctrl (en&zh)](https://www.modelscope.cn/datasets/deepctrl/deepctrl-sft-data)\n- [Advertise Generating (zh)](https://huggingface.co/datasets/HasturOfficial/adgen)\n- [ShareGPT Hyperfiltered (en)](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k)\n- [ShareGPT4 (en&zh)](https://huggingface.co/datasets/shibing624/sharegpt_gpt4)\n- [UltraChat 200k (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)\n- [AgentInstruct (en)](https://huggingface.co/datasets/THUDM/AgentInstruct)\n- [LMSYS Chat 1M (en)](https://huggingface.co/datasets/lmsys/lmsys-chat-1m)\n- [Evol Instruct V2 (en)](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)\n- [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia)\n- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)\n- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)\n- [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)\n- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)\n- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)\n- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)\n- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)\n- [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)\n- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)\n- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)\n- [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)\n- [OpenSchnabeltier (de)](https://huggingface.co/datasets/mayflowergmbh/openschnabeltier_de)\n- [Evol Instruct (de)](https://huggingface.co/datasets/mayflowergmbh/evol-instruct_de)\n- [Dolphin (de)](https://huggingface.co/datasets/mayflowergmbh/dolphin_de)\n- [Booksum (de)](https://huggingface.co/datasets/mayflowergmbh/booksum_de)\n- [Airoboros (de)](https://huggingface.co/datasets/mayflowergmbh/airoboros-3.0_de)\n- [Ultrachat (de)](https://huggingface.co/datasets/mayflowergmbh/ultra-chat_de)\n\n</details>\n\n<details><summary>Preference datasets</summary>\n\n- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)\n- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)\n- [RLHF-V (en)](https://huggingface.co/datasets/openbmb/RLHF-V-Dataset)\n- [VLFeedback (en)](https://huggingface.co/datasets/Zhihui/VLFeedback)\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- [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\n</details>\n\nSome 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## Requirement\n\n| Mandatory    | Minimum | Recommend |\n| ------------ | ------- | --------- |\n| python       | 3.8     | 3.11      |\n| torch        | 1.13.1  | 2.4.0     |\n| transformers | 4.41.2  | 4.43.4    |\n| datasets     | 2.16.0  | 2.20.0    |\n| accelerate   | 0.30.1  | 0.32.0    |\n| peft         | 0.11.1  | 0.12.0    |\n| trl          | 0.8.6   | 0.9.6     |\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         | 0.4.3   | 0.5.0     |\n| flash-attn   | 2.3.0   | 2.6.3     |\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## Getting Started\n\n### Installation\n\n> [!IMPORTANT]\n> Installation is mandatory.\n\n```bash\ngit clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git\ncd LLaMA-Factory\npip install -e \".[torch,metrics]\"\n```\n\nExtra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, quality\n\n> [!TIP]\n> Use `pip install --no-deps -e .` to resolve package conflicts.\n\n<details><summary>For Windows users</summary>\n\nIf you want to enable the quantized LoRA (QLoRA) on the Windows platform, you need to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.2, please select the appropriate [release version](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels) based on your CUDA version.\n\n```bash\npip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.2.post2-py3-none-win_amd64.whl\n```\n\nTo enable FlashAttention-2 on the Windows platform, you need to install the precompiled `flash-attn` library, which supports CUDA 12.1 to 12.2. Please download the corresponding version from [flash-attention](https://github.com/bdashore3/flash-attention/releases) based on your requirements.\n\n</details>\n\n<details><summary>For Ascend NPU users</summary>\n\nTo install LLaMA Factory on Ascend NPU devices, please specify extra dependencies: `pip install -e \".[torch-npu,metrics]\"`. Additionally, you need to install the **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**. Please follow the [installation tutorial](https://www.hiascend.com/document/detail/en/CANNCommunityEdition/600alphaX/softwareinstall/instg/atlasdeploy_03_0031.html) or use the following commands:\n\n```bash\n# replace the url according to your CANN version and devices\n# install CANN Toolkit\nwget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-toolkit_8.0.RC1.alpha001_linux-\"$(uname -i)\".run\nbash Ascend-cann-toolkit_8.0.RC1.alpha001_linux-\"$(uname -i)\".run --install\n\n# install CANN Kernels\nwget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C17SPC701/Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run\nbash Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run --install\n\n# set env variables\nsource /usr/local/Ascend/ascend-toolkit/set_env.sh\n```\n\n| Requirement  | Minimum | Recommend   |\n| ------------ | ------- | ----------- |\n| CANN         | 8.0.RC1 | 8.0.RC1     |\n| torch        | 2.1.0   | 2.1.0       |\n| torch-npu    | 2.1.0   | 2.1.0.post3 |\n| deepspeed    | 0.13.2  | 0.13.2      |\n\nRemember to use `ASCEND_RT_VISIBLE_DEVICES` instead of `CUDA_VISIBLE_DEVICES` to specify the device to use.\n\nIf you cannot infer model on NPU devices, try setting `do_sample: false` in the configurations.\n\nDownload the pre-built Docker images: [32GB](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html) | [64GB](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)\n\n</details>\n\n### Data Preparation\n\nPlease refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope hub or load the dataset in local disk.\n\n> [!NOTE]\n> Please update `data/dataset_info.json` to use your custom dataset.\n\n### Quickstart\n\nUse the following 3 commands to run LoRA **fine-tuning**, **inference** and **merging** of the Llama3-8B-Instruct model, respectively.\n\n```bash\nllamafactory-cli train examples/train_lora/llama3_lora_sft.yaml\nllamafactory-cli chat examples/inference/llama3_lora_sft.yaml\nllamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml\n```\n\nSee [examples/README.md](examples/README.md) for advanced usage (including distributed training).\n\n> [!TIP]\n> Use `llamafactory-cli help` to show help information.\n\n### Fine-Tuning with LLaMA Board GUI (powered by [Gradio](https://github.com/gradio-app/gradio))\n\n```bash\nllamafactory-cli webui\n```\n\n### Build Docker\n\nFor CUDA users:\n\n```bash\ncd docker/docker-cuda/\ndocker compose up -d\ndocker compose exec llamafactory bash\n```\n\nFor Ascend NPU users:\n\n```bash\ncd docker/docker-npu/\ndocker compose up -d\ndocker compose exec llamafactory bash\n```\n\nFor AMD ROCm users:\n\n```bash\ncd docker/docker-rocm/\ndocker compose up -d\ndocker compose exec llamafactory bash\n```\n\n<details><summary>Build without Docker Compose</summary>\n\nFor CUDA users:\n\n```bash\ndocker build -f ./docker/docker-cuda/Dockerfile \\\n    --build-arg INSTALL_BNB=false \\\n    --build-arg INSTALL_VLLM=false \\\n    --build-arg INSTALL_DEEPSPEED=false \\\n    --build-arg INSTALL_FLASHATTN=false \\\n    --build-arg PIP_INDEX=https://pypi.org/simple \\\n    -t llamafactory:latest .\n\ndocker run -dit --gpus=all \\\n    -v ./hf_cache:/root/.cache/huggingface \\\n    -v ./ms_cache:/root/.cache/modelscope \\\n    -v ./data:/app/data \\\n    -v ./output:/app/output \\\n    -p 7860:7860 \\\n    -p 8000:8000 \\\n    --shm-size 16G \\\n    --name llamafactory \\\n    llamafactory:latest\n\ndocker exec -it llamafactory bash\n```\n\nFor Ascend NPU users:\n\n```bash\n# Choose docker image upon your environment\ndocker build -f ./docker/docker-npu/Dockerfile \\\n    --build-arg INSTALL_DEEPSPEED=false \\\n    --build-arg PIP_INDEX=https://pypi.org/simple \\\n    -t llamafactory:latest .\n\n# Change `device` upon your resources\ndocker run -dit \\\n    -v ./hf_cache:/root/.cache/huggingface \\\n    -v ./ms_cache:/root/.cache/modelscope \\\n    -v ./data:/app/data \\\n    -v ./output:/app/output \\\n    -v /usr/local/dcmi:/usr/local/dcmi \\\n    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \\\n    -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \\\n    -v /etc/ascend_install.info:/etc/ascend_install.info \\\n    -p 7860:7860 \\\n    -p 8000:8000 \\\n    --device /dev/davinci0 \\\n    --device /dev/davinci_manager \\\n    --device /dev/devmm_svm \\\n    --device /dev/hisi_hdc \\\n    --shm-size 16G \\\n    --name llamafactory \\\n    llamafactory:latest\n\ndocker exec -it llamafactory bash\n```\n\nFor AMD ROCm users:\n\n```bash\ndocker build -f ./docker/docker-rocm/Dockerfile \\\n    --build-arg INSTALL_BNB=false \\\n    --build-arg INSTALL_VLLM=false \\\n    --build-arg INSTALL_DEEPSPEED=false \\\n    --build-arg INSTALL_FLASHATTN=false \\\n    --build-arg PIP_INDEX=https://pypi.org/simple \\\n    -t llamafactory:latest .\n\ndocker run -dit \\\n    -v ./hf_cache:/root/.cache/huggingface \\\n    -v ./ms_cache:/root/.cache/modelscope \\\n    -v ./data:/app/data \\\n    -v ./output:/app/output \\\n    -v ./saves:/app/saves \\\n    -p 7860:7860 \\\n    -p 8000:8000 \\\n    --device /dev/kfd \\\n    --device /dev/dri \\\n    --shm-size 16G \\\n    --name llamafactory \\\n    llamafactory:latest\n\ndocker exec -it llamafactory bash\n```\n\n</details>\n\n<details><summary>Details about volume</summary>\n\n- `hf_cache`: Utilize Hugging Face cache on the host machine. Reassignable if a cache already exists in a different directory.\n- `ms_cache`: Similar to Hugging Face cache but for ModelScope users.\n- `data`: Place datasets on this dir of the host machine so that they can be selected on LLaMA Board GUI.\n- `output`: Set export dir to this location so that the merged result can be accessed directly on the host machine.\n\n</details>\n\n### Deploy with OpenAI-style API and vLLM\n\n```bash\nAPI_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml\n```\n\n> [!TIP]\n> Visit [this page](https://platform.openai.com/docs/api-reference/chat/create) for API document.\n\n### Download from ModelScope Hub\n\nIf you have trouble with downloading models and datasets from Hugging Face, you can use ModelScope.\n\n```bash\nexport USE_MODELSCOPE_HUB=1 # `set USE_MODELSCOPE_HUB=1` for Windows\n```\n\nTrain the model by specifying a model ID of the ModelScope Hub as the `model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `LLM-Research/Meta-Llama-3-8B-Instruct`.\n\n### Use W&B Logger\n\nTo use [Weights & Biases](https://wandb.ai) for logging experimental results, you need to add the following arguments to yaml files.\n\n```yaml\nreport_to: wandb\nrun_name: test_run # optional\n```\n\nSet `WANDB_API_KEY` to [your key](https://wandb.ai/authorize) when launching training tasks to log in with your W&B account.\n\n## Projects using LLaMA Factory\n\nIf you have a project that should be incorporated, please contact via email or create a pull request.\n\n<details><summary>Click to show</summary>\n\n1. Wang et al. ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. 2023. [[arxiv]](https://arxiv.org/abs/2308.02223)\n1. Yu et al. Open, Closed, or Small Language Models for Text Classification? 2023. [[arxiv]](https://arxiv.org/abs/2308.10092)\n1. Wang et al. UbiPhysio: Support Daily Functioning, Fitness, and Rehabilitation with Action Understanding and Feedback in Natural Language. 2023. [[arxiv]](https://arxiv.org/abs/2308.10526)\n1. Luceri et al. Leveraging Large Language Models to Detect Influence Campaigns in Social Media. 2023. [[arxiv]](https://arxiv.org/abs/2311.07816)\n1. Zhang et al. Alleviating Hallucinations of Large Language Models through Induced Hallucinations. 2023. [[arxiv]](https://arxiv.org/abs/2312.15710)\n1. Wang et al. Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs. KDD 2024. [[arxiv]](https://arxiv.org/abs/2401.04319)\n1. Wang et al. CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning. ACL 2024. [[arxiv]](https://arxiv.org/abs/2401.07286)\n1. Choi et al. FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2402.05904)\n1. Zhang et al. AutoMathText: Autonomous Data Selection with Language Models for Mathematical Texts. 2024. [[arxiv]](https://arxiv.org/abs/2402.07625)\n1. Lyu et al. KnowTuning: Knowledge-aware Fine-tuning for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.11176)\n1. Yang et al. LaCo: Large Language Model Pruning via Layer Collaps. 2024. [[arxiv]](https://arxiv.org/abs/2402.11187)\n1. Bhardwaj et al. Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic. 2024. [[arxiv]](https://arxiv.org/abs/2402.11746)\n1. Yang et al. Enhancing Empathetic Response Generation by Augmenting LLMs with Small-scale Empathetic Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.11801)\n1. Yi et al. Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding. ACL 2024 Findings. [[arxiv]](https://arxiv.org/abs/2402.11809)\n1. Cao et al. Head-wise Shareable Attention for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.11819)\n1. Zhang et al. Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages. 2024. [[arxiv]](https://arxiv.org/abs/2402.12204)\n1. Kim et al. Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2402.14714)\n1. Yu et al. KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models. ACL 2024. [[arxiv]](https://arxiv.org/abs/2402.15043)\n1. Huang et al. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2403.02333)\n1. Duan et al. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. 2024. [[arxiv]](https://arxiv.org/abs/2403.03419)\n1. Xie and Schwertfeger. Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2403.08228)\n1. Wu et al. Large Language Models are Parallel Multilingual Learners. 2024. [[arxiv]](https://arxiv.org/abs/2403.09073)\n1. Zhang et al. EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling. 2024. [[arxiv]](https://arxiv.org/abs/2403.14541)\n1. Weller et al. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2403.15246)\n1. Hongbin Na. CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering. COLING 2024. [[arxiv]](https://arxiv.org/abs/2403.16008)\n1. Zan et al. CodeS: Natural Language to Code Repository via Multi-Layer Sketch. 2024. [[arxiv]](https://arxiv.org/abs/2403.16443)\n1. Liu et al. Extensive Self-Contrast Enables Feedback-Free Language Model Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2404.00604)\n1. Luo et al. BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.02827)\n1. Du et al. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2404.04167)\n1. Ma et al. Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation. ICML 2024. [[arxiv]](https://arxiv.org/abs/2404.04316)\n1. Liu et al. Dynamic Generation of Personalities with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.07084)\n1. Shang et al. How Far Have We Gone in Stripped Binary Code Understanding Using Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.09836)\n1. Huang et al. LLMTune: Accelerate Database Knob Tuning with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.11581)\n1. Deng et al. Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction. 2024. [[arxiv]](https://arxiv.org/abs/2404.14215)\n1. Acikgoz et al. Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare. 2024. [[arxiv]](https://arxiv.org/abs/2404.16621)\n1. Zhang et al. Small Language Models Need Strong Verifiers to Self-Correct Reasoning. ACL 2024 Findings. [[arxiv]](https://arxiv.org/abs/2404.17140)\n1. Zhou et al. FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering. NAACL 2024. [[arxiv]](https://arxiv.org/abs/2404.18585)\n1. Xu et al. Large Language Models for Cyber Security: A Systematic Literature Review. 2024. [[arxiv]](https://arxiv.org/abs/2405.04760)\n1. Dammu et al. \"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations. 2024. [[arxiv]](https://arxiv.org/abs/2405.05378)\n1. Yi et al. A safety realignment framework via subspace-oriented model fusion for large language models. 2024. [[arxiv]](https://arxiv.org/abs/2405.09055)\n1. Lou et al. SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling. 2024. [[arxiv]](https://arxiv.org/abs/2405.12739)\n1. Zhang et al. Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners. 2024. [[arxiv]](https://arxiv.org/abs/2405.13816)\n1. Zhang et al. TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2405.20215)\n1. Zihong Chen. Sentence Segmentation and Sentence Punctuation Based on XunziALLM. 2024. [[paper]](https://aclanthology.org/2024.lt4hala-1.30)\n1. Gao et al. The Best of Both Worlds: Toward an Honest and Helpful Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2406.00380)\n1. Wang and Song. MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset. 2024. [[arxiv]](https://arxiv.org/abs/2406.02106)\n1. Hu et al. Computational Limits of Low-Rank Adaptation (LoRA) for Transformer-Based Models. 2024. [[arxiv]](https://arxiv.org/abs/2406.03136)\n1. Ge et al. Time Sensitive Knowledge Editing through Efficient Finetuning. ACL 2024. [[arxiv]](https://arxiv.org/abs/2406.04496)\n1. Tan et al. Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions. 2024. [[arxiv]](https://arxiv.org/abs/2406.05688)\n1. Song et al. Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters. 2024. [[arxiv]](https://arxiv.org/abs/2406.05955)\n1. Gu et al. RWKV-CLIP: A Robust Vision-Language Representation Learner. 2024. [[arxiv]](https://arxiv.org/abs/2406.06973)\n1. Chen et al. Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees. 2024. [[arxiv]](https://arxiv.org/abs/2406.07115)\n1. Zhu et al. Are Large Language Models Good Statisticians?. 2024. [[arxiv]](https://arxiv.org/abs/2406.07815)\n1. Li et al. Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning. 2024. [[arxiv]](https://arxiv.org/abs/2406.10099)\n1. Ding et al. IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce. 2024. [[arxiv]](https://arxiv.org/abs/2406.10173)\n1. He et al. COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communities. 2024. [[arxiv]](https://arxiv.org/abs/2406.12074)\n1. Lin et al. FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving. 2024. [[arxiv]](https://arxiv.org/abs/2406.14408)\n1. Treutlein et al. Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data. 2024. [[arxiv]](https://arxiv.org/abs/2406.14546)\n1. Feng et al. SS-Bench: A Benchmark for Social Story Generation and Evaluation. 2024. [[arxiv]](https://arxiv.org/abs/2406.15695)\n1. Feng et al. Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement. 2024. [[arxiv]](https://arxiv.org/abs/2406.17233)\n1. Liu et al. Large Language Models for Cuffless Blood Pressure Measurement From Wearable Biosignals. 2024. [[arxiv]](https://arxiv.org/abs/2406.18069)\n1. Iyer et al. Exploring Very Low-Resource Translation with LLMs: The University of Edinburgh's Submission to AmericasNLP 2024 Translation Task. AmericasNLP 2024. [[paper]](https://aclanthology.org/2024.americasnlp-1.25)\n1. Li et al. Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring. 2024. [[arxiv]](https://arxiv.org/abs/2406.19949)\n1. Yang et al. Financial Knowledge Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2407.00365)\n1. Lin et al. DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging. 2024. [[arxiv]](https://arxiv.org/abs/2407.01470)\n1. Bako et al. Evaluating the Semantic Profiling Abilities of LLMs for Natural Language Utterances in Data Visualization. 2024. [[arxiv]](https://arxiv.org/abs/2407.06129)\n1. Huang et al. RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization. 2024. [[arxiv]](https://arxiv.org/abs/2407.08044)\n1. Jiang et al. LLM-Collaboration on Automatic Science Journalism for the General Audience. 2024. [[arxiv]](https://arxiv.org/abs/2407.09756)\n1. Inouye et al. Applied Auto-tuning on LoRA Hyperparameters. 2024. [[paper]](https://scholarcommons.scu.edu/cseng_senior/272/)\n1. Qi et al. Research on Tibetan Tourism Viewpoints information generation system based on LLM. 2024. [[arxiv]](https://arxiv.org/abs/2407.13561)\n1. Xu et al. Course-Correction: Safety Alignment Using Synthetic Preferences. 2024. [[arxiv]](https://arxiv.org/abs/2407.16637)\n1. Sun et al. LAMBDA: A Large Model Based Data Agent. 2024. [[arxiv]](https://arxiv.org/abs/2407.17535)\n1. Zhu et al. CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare. 2024. [[arxiv]](https://arxiv.org/abs/2407.19705)\n1. Yu et al. Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2408.00137)\n1. Xie et al. The Power of Personalized Datasets: Advancing Chinese Composition Writing for Elementary School through Targeted Model Fine-Tuning. IALP 2024. [[paper]](https://www.asianlp.sg/conferences/ialp2024/proceedings/papers/IALP2024_P055.pdf)\n1. Liu et al. Instruct-Code-Llama: Improving Capabilities of Language Model in Competition Level Code Generation by Online Judge Feedback. ICIC 2024. [[paper]](https://link.springer.com/chapter/10.1007/978-981-97-5669-8_11)\n1. Wang et al. Cybernetic Sentinels: Unveiling the Impact of Safety Data Selection on Model Security in Supervised Fine-Tuning. ICIC 2024. [[paper]](https://link.springer.com/chapter/10.1007/978-981-97-5669-8_23)\n1. Xia et al. Understanding the Performance and Estimating the Cost of LLM Fine-Tuning. 2024. [[arxiv]](https://arxiv.org/abs/2408.04693)\n1. Zeng et al. Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2408.04168)\n1. Xia et al. Using Pre-trained Language Model for Accurate ESG Prediction. FinNLP 2024. [[paper]](https://aclanthology.org/2024.finnlp-2.1/)\n1. Liang et al. I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm. 2024. [[arxiv]](https://arxiv.org/abs/2408.08072)\n1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: A large language model for Astronomy, based on ChatGLM2-6B and Qwen-14B.\n1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: A large language model specialized in Chinese legal domain, based on Baichuan-13B, is capable of retrieving and reasoning on legal knowledge.\n1. **[Sunsimiao](https://github.com/X-D-Lab/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B.\n1. **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: A series of large language models for Chinese medical domain, based on LLaMA2-7B and Baichuan-13B.\n1. **[MachineMindset](https://github.com/PKU-YuanGroup/Machine-Mindset/)**: A series of MBTI Personality large language models, capable of giving any LLM 16 different personality types based on different datasets and training methods.\n1. **[Luminia-13B-v3](https://huggingface.co/Nekochu/Luminia-13B-v3)**: A large language model specialized in generate metadata for stable diffusion. [[\ud83e\udd17Demo]](https://huggingface.co/spaces/Nekochu/Luminia-13B_SD_Prompt)\n1. **[Chinese-LLaVA-Med](https://github.com/BUAADreamer/Chinese-LLaVA-Med)**: A multimodal large language model specialized in Chinese medical domain, based on LLaVA-1.5-7B.\n1. **[AutoRE](https://github.com/THUDM/AutoRE)**: A document-level relation extraction system based on large language models.\n1. **[NVIDIA RTX AI Toolkit](https://github.com/NVIDIA/RTX-AI-Toolkit)**: SDKs for fine-tuning LLMs on Windows PC for NVIDIA RTX.\n1. **[LazyLLM](https://github.com/LazyAGI/LazyLLM)**: An easy and lazy way for building multi-agent LLMs applications and supports model fine-tuning via LLaMA Factory.\n\n</details>\n\n## License\n\nThis repository is licensed under the [Apache-2.0 License](LICENSE).\n\nPlease follow the model licenses to use the corresponding model weights: [Baichuan 2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)\n\n## Citation\n\nIf this work is helpful, please kindly cite as:\n\n```bibtex\n@inproceedings{zheng2024llamafactory,\n  title={LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models},\n  author={Yaowei Zheng and Richong Zhang and Junhao Zhang and Yanhan Ye and Zheyan Luo and Zhangchi Feng and Yongqiang Ma},\n  booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},\n  address={Bangkok, Thailand},\n  publisher={Association for Computational Linguistics},\n  year={2024},\n  url={http://arxiv.org/abs/2403.13372}\n}\n```\n\n## Acknowledgement\n\nThis repo benefits from [PEFT](https://github.com/huggingface/peft), [TRL](https://github.com/huggingface/trl), [QLoRA](https://github.com/artidoro/qlora) and [FastChat](https://github.com/lm-sys/FastChat). Thanks for their wonderful works.\n\n## Star History\n\n![Star History Chart](https://api.star-history.com/svg?repos=hiyouga/LLaMA-Factory&type=Date)\n",
    "bugtrack_url": null,
    "license": "Apache 2.0 License",
    "summary": "Easy-to-use LLM fine-tuning framework",
    "version": "0.9.0",
    "project_urls": {
        "Homepage": "https://github.com/hiyouga/LLaMA-Factory"
    },
    "split_keywords": [
        "llama",
        " bloom",
        " falcon",
        " llm",
        " chatgpt",
        " transformer",
        " pytorch",
        " deep learning"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "704544f0f72d1a0737e2b3f1fead3803fe2f24ae8345f0f38132eebefa0f4197",
                "md5": "8d7179de60272efb58ce26f57b834114",
                "sha256": "6e34230b3ea09285b35faf71bd234fe21e478e3d7b41e25e3368f6aa2d0563a9"
            },
            "downloads": -1,
            "filename": "llamafactory-0.9.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "8d7179de60272efb58ce26f57b834114",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8.0",
            "size": 245842,
            "upload_time": "2024-09-08T17:14:47",
            "upload_time_iso_8601": "2024-09-08T17:14:47.562808Z",
            "url": "https://files.pythonhosted.org/packages/70/45/44f0f72d1a0737e2b3f1fead3803fe2f24ae8345f0f38132eebefa0f4197/llamafactory-0.9.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "81d16ba5f3b7f7b8fc492b5358116199ff4484e9ffbce3460fe40f315458237b",
                "md5": "110231b0d5f1a32102e7f409931a6c4a",
                "sha256": "93b2c428034106a75130d8567ae6b34d508f560d7b3baee6bb9e72f664cd1bba"
            },
            "downloads": -1,
            "filename": "llamafactory-0.9.0.tar.gz",
            "has_sig": false,
            "md5_digest": "110231b0d5f1a32102e7f409931a6c4a",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8.0",
            "size": 194648,
            "upload_time": "2024-09-08T17:14:49",
            "upload_time_iso_8601": "2024-09-08T17:14:49.501580Z",
            "url": "https://files.pythonhosted.org/packages/81/d1/6ba5f3b7f7b8fc492b5358116199ff4484e9ffbce3460fe40f315458237b/llamafactory-0.9.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-09-08 17:14:49",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "hiyouga",
    "github_project": "LLaMA-Factory",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [],
    "lcname": "llamafactory"
}
        
Elapsed time: 0.37007s