update to v0.9.1

27a7ad86 · luopl · 731cf9b8 · 27a7ad86 · 27a7ad86 · 27a7ad86
Commit 27a7ad86 authored Oct 14, 2024 by luopl
20 changed files
--- a/.env.local
+++ b/.env.local
+# Note: actually we do not support .env, just for reference
+# api
+API_HOST=0.0.0.0
+API_PORT=8000
+API_KEY=
+API_MODEL_NAME=gpt-3.5-turbo
+FASTAPI_ROOT_PATH=
+# general
+DISABLE_VERSION_CHECK=
+FORCE_CHECK_IMPORTS=
+LLAMAFACTORY_VERBOSITY=
+USE_MODELSCOPE_HUB=
+RECORD_VRAM=
+# torchrun
+FORCE_TORCHRUN=
+MASTER_ADDR=
+MASTER_PORT=
+NNODES=
+RANK=
+NPROC_PER_NODE=
+# wandb
+WANDB_DISABLED=
+WANDB_PROJECT=huggingface
+WANDB_API_KEY=
+# gradio ui
+GRADIO_SHARE=False
+GRADIO_SERVER_NAME=0.0.0.0
+GRADIO_SERVER_PORT=
+GRADIO_ROOT_PATH=
+# setup
+ENABLE_SHORT_CONSOLE=1
+# reserved (do not use)
+LLAMABOARD_ENABLED=
+LLAMABOARD_WORKDIR=
--- a/Makefile
+++ b/Makefile
 .PHONY: quality style test

-check_dirs := scripts src tests
+check_dirs := scripts src tests setup.py

 quality:
 	ruff check $(check_dirs)

--- a/README.md
+++ b/README.md
-# <div align="center"><strong>LLaMA Factory</strong></div>
-## 简介
+![# LLaMA Factory](assets/logo.png)

-LLaMA Factory是一个大语言模型训练和推理的框架，支持了魔搭社区（ModelScope）的模型和数据集资源。它允许用户通过内置的Web UI灵活定制100多个LLMs的微调，而无需编写代码。
+[![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)

-## 项目特色
+[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)

- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
- **集成方法**：（增量）预训练、（多模态）指令监督微调、奖励模型训练、PPO 训练、DPO 训练、KTO 训练、ORPO 训练等等。
- **多种精度**：16 比特全参数微调、冻结微调、LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ 的 2/3/4/5/6/8 比特 QLoRA 微调。
- **先进算法**：GaLore、BAdam、Adam-mini、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
- **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune 和 rsLoRA。
- **实验监控**：LlamaBoard、TensorBoard、Wandb、MLflow 等等。
- **极速推理**：基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。
+👋 Join our [WeChat](assets/wechat.jpg) or [NPU user group](assets/wechat_npu.jpg).

-## 支持模型结构列表
+\[ English | [中文](README_zh.md) \]

-| 模型名                                                       | 模型大小                          | Template  |
-| ------------------------------------------------------------ | -------------------------------- | --------- |
-| [Baichuan 2](https://huggingface.co/baichuan-inc)            | 7B/13B                           | baichuan2 |
-| [Gemma 2](https://huggingface.co/google)                     | 2B/9B                            | gemma     |
-| [Llama 2](https://huggingface.co/meta-llama)                 | 7B/13B/70B                       | llama2    |
-| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama)       | 8B/70B                           | llama3    |
-| [Qwen1.5 (Code/MoE)/Qwen2](https://huggingface.co/Qwen)            | 0.5B/1.8B/4B/7B/14B/32B/72B      | qwen      |
-| [XVERSE](https://hf-mirror.com/xverse)                       | 7B/13B                           | xverse    |
-| [OLMo](https://hf-mirror.com/allenai)                        | 1B/7B                            | olmo      |
+**Fine-tuning a large language model can be easy as...**

-持续更新中...
+https://github.com/user-attachments/assets/7c96b465-9df7-45f4-8053-bf03e58386d3

-> 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
->
-> 请务必在训练和推理时采用**完全一致**的模板。
+Choose your path:

-您也可以在 [template.py](src/llamafactory/data/template.py) 中添加自己的对话模板。
+- **Colab**: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing
+- **PAI-DSW**: [Llama3 Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl)
+- **Local machine**: Please refer to [usage](#getting-started)
+- **Documentation (WIP)**: https://llamafactory.readthedocs.io/zh-cn/latest/

-> **[!NOTE]**
->
-> 1. `Baichuan 2` 需要卸载掉环境中的xformers库，当前仅支持Lora方式训练。
->
-> 2. `XVERSE`在`tokenizer > 0.19`的版本下有兼容性问题报错`Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrappe`，需要使用[XVERSE-13B-256K-hf](https://huggingface.co/xverse/XVERSE-13B-256K/tree/main)中的`tokenizer_config.json.update`/`tokenizer.json.update`替换原有模型文件中的对应tokenizer文件，具体解决方法参考[xverse-ai/XVERSE-7B issues](https://github.com/xverse-ai/XVERSE-7B/issues/1)
+> [!NOTE]
+> Except for the above links, all other websites are unauthorized third-party websites. Please carefully use them.
+
+## 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
+
+[24/09/19] We support fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models.
+
+[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 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3           |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava            |
+| [LLaVA-NeXT](https://huggingface.co/llava-hf)                     | 7B/8B/13B/34B/72B/110B           | llava_next       |
+| [LLaVA-NeXT-Video](https://huggingface.co/llava-hf)               | 7B/34B                           | llava_next_video |
+| [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 (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
+| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | 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.
 >
-> 3. `Qwen2`训练仅支持bf16格式，**fp16会出现loss为0，lr为0的问题**，参考[issues](https://github.com/hiyouga/LLaMA-Factory/issues/4848)
+> Remember to use the **SAME** template in training and inference.

-## 使用源码编译方式安装
-### 环境准备
+Please refer to [constants.py](src/llamafactory/extras/constants.py) for a full list of models we supported.

-v 路径、docker_name和imageID根据实际情况修改
+You also can add a custom chat template to [template.py](src/llamafactory/data/template.py).

-####  Docker（方法一）
+## Supported Training Approaches

-基于光源pytorch2.1.0基础镜像环境：镜像下载地址：[https://sourcefind.cn/#/image/dcu/pytorch](https://sourcefind.cn/#/image/dcu/pytorch)，根据pytorch2.1.0、python、dtk及系统下载对应的镜像版本。
+| 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: |

-```bash
-docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
-docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+> [!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.

-pip install vllm-0.5.0+das.opt1.3e2c63a.dtk2404.torch2.1.0-cp310-cp310-linux_x86_64.whl
-pip install lmslim-0.0.1+das.dtk24041.torch2.1.0-cp310-cp310-linux_x86_64.whl
+```bash
+pip install --upgrade huggingface_hub
+huggingface-cli login
 ```

-#### Dockerfile（方法二）
+## Requirement

-```bash
-cd docker
-docker build --no-cache -t llama-factory:latest .
-docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+| 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     |

-pip install vllm-0.5.0+das.opt1.3e2c63a.dtk2404.torch2.1.0-cp310-cp310-linux_x86_64.whl
-pip install lmslim-0.0.1+das.dtk24041.torch2.1.0-cp310-cp310-linux_x86_64.whl
-```
+| 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

-#### Anaconda（方法三）
+### Installation
+
+> [!IMPORTANT]
+> Installation is mandatory.

-关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
 ```bash
-DTK驱动: dtk24.04.1
-python: 3.10
-torch: 2.1.0
-bitsandbytes: 0.42.0
-vllm: 0.5.0
-lmslim: 0.0.1
+git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
+cd LLaMA-Factory
+pip install -e ".[torch,metrics]"
 ```
-`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`

-### 源码编译安装
+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]
-> 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
+> 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
-git clone http://developer.hpccube.com/codes/OpenDAS/llama-factory.git
-cd /your_code_path/llama_factory
-pip install -e ".[torch,metrics]"
+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>

-# pdsh安装，deepspeed多机需要，若已安装，可忽略。
-# 安装需要root权限
-cd ../
-#下载解压
-wget https://storage.googleapis.com/google-code-archive-downloads/v2/code.google.com/pdsh/pdsh-2.29.tar.bz2 && tar -xf pdsh-2.29.tar.bz2
-#编译安装
-cd pdsh-2.29 && ./configure --with-ssh --enable-static-modules --prefix=/usr/local && make && make install
-#测试
-pdsh -V
+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
 ```

-## 如何使用
-### 数据准备
+| 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

-关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace / ModelScope 上的数据集或加载本地数据集。
+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]
-> 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
+> Please update `data/dataset_info.json` to use your custom dataset.

-### 快速开始
+### Quickstart

-下面三行命令分别对 Llama3-8B-Instruct 模型进行 LoRA **微调**、**推理**和**合并**。根据实际情况修改参数，如`model_name_or_path`/`dataset`/`template`等。
+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
@@ -121,12 +430,297 @@ llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
 llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
 ```

-高级用法请参考 [examples/README_zh.md](examples/README_zh.md)（包括多 GPU 微调）。
+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]
-> 使用 `llamafactory-cli help` 显示帮助信息。
+> 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.

-## 参考资料
+## Star History

- [README_zh](README_zh.md)
- [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
+![Star History Chart](https://api.star-history.com/svg?repos=hiyouga/LLaMA-Factory&type=Date)
--- a/README_zh.md
+++ b/README_zh.md
@@ -26,11 +26,14 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 选择你的打开方式：

 - **Colab**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing
- **PAI-DSW**：https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
+- **PAI-DSW**：[Llama3 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl)
 - **本地机器**：请见[如何使用](#如何使用)
 - **入门教程**：https://zhuanlan.zhihu.com/p/695287607
 - **框架文档**：https://llamafactory.readthedocs.io/zh-cn/latest/

+> [!NOTE]
+> 除上述链接以外的其他网站均为未经许可的第三方网站，请小心甄别。
+
 ## 目录

 - [项目特色](#项目特色)
@@ -48,11 +51,11 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272

 ## 项目特色

- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
+- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Qwen2-VL、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
 - **集成方法**：（增量）预训练、（多模态）指令监督微调、奖励模型训练、PPO 训练、DPO 训练、KTO 训练、ORPO 训练等等。
 - **多种精度**：16 比特全参数微调、冻结微调、LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ 的 2/3/4/5/6/8 比特 QLoRA 微调。
- **先进算法**：GaLore、BAdam、Adam-mini、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
- **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune 和 rsLoRA。
+- **先进算法**：[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 和 Agent 微调。
+- **实用技巧**：[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 和 rsLoRA。
 - **实验监控**：LlamaBoard、TensorBoard、Wandb、MLflow 等等。
 - **极速推理**：基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。

@@ -73,19 +76,25 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272

 ## 更新日志

-[24/08/09] 我们支持了 **[Adam-mini](https://arxiv.org/abs/2406.16793)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。
+[24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。

-[24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。
+[24/08/30] 我们支持了 **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** 模型的微调。感谢 [@simonJJJ](https://github.com/simonJJJ) 的 PR。

-[24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。
+[24/08/27] 我们支持了 **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**。请使用 `enable_liger_kernel: true` 来加速训练。
+
+[24/08/09] 我们支持了 **[Adam-mini](https://github.com/zyushun/Adam-mini)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。

 <details><summary>展开日志</summary>

+[24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。
+
+[24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。
+
 [24/06/07] 我们支持了 **[Qwen2](https://qwenlm.github.io/blog/qwen2/)** 和 **[GLM-4](https://github.com/THUDM/GLM-4)** 模型的微调。

 [24/05/26] 我们支持了 **[SimPO](https://arxiv.org/abs/2405.14734)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。

-[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `gemma` 模板进行微调使其获得对话能力。
+[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `paligemma` 模板进行微调使其获得对话能力。

 [24/05/18] 我们支持了 **[KTO](https://arxiv.org/abs/2402.01306)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。

@@ -157,33 +166,36 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272

 ## 模型

-| 模型名                                                            | 模型大小                          | 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                           | vicuna    |
-| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B                            | cpm       |
-| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral   |
-| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -         |
-| [PaliGemma](https://huggingface.co/google)                        | 3B                               | gemma     |
-| [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      |
-| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -         |
-| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse    |
-| [Yi/Yi-1.5](https://huggingface.co/01-ai)                         | 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      |
+| 模型名                                                            | 模型大小                          | 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 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3           |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava            |
+| [LLaVA-NeXT](https://huggingface.co/llava-hf)                     | 7B/8B/13B/34B/72B/110B           | llava_next       |
+| [LLaVA-NeXT-Video](https://huggingface.co/llava-hf)               | 7B/34B                           | llava_next_video |
+| [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 (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
+| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | 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]
 > 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
@@ -271,6 +283,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [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)
@@ -287,6 +300,8 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272

 - [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)
@@ -349,7 +364,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```

-可选的额外依赖项：torch、torch-npu、metrics、deepspeed、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality
+可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality

 > [!TIP]
 > 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。

--- a/assets/wechat.jpg
+++ b/assets/wechat.jpg
--- a/assets/wechat_npu.jpg
+++ b/assets/wechat_npu.jpg
--- a/data/README.md
+++ b/data/README.md
@@ -23,6 +23,7 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
    "system": "the column name in the dataset containing the system prompts. (default: None)",
    "tools": "the column name in the dataset containing the tool description. (default: None)",
    "images": "the column name in the dataset containing the image inputs. (default: None)",
+    "videos": "the column name in the dataset containing the videos inputs. (default: None)",
    "chosen": "the column name in the dataset containing the chosen answers. (default: None)",
    "rejected": "the column name in the dataset containing the rejected answers. (default: None)",
    "kto_tag": "the column name in the dataset containing the kto tags. (default: None)"
@@ -107,7 +108,7 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh

 ### Preference Dataset

-Preference datasets are used for reward modeling, DPO training and ORPO training.
+Preference datasets are used for reward modeling, DPO training, ORPO and SimPO training.

 It requires a better response in `chosen` column and a worse response in `rejected` column.

@@ -139,67 +140,15 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh

 ### KTO Dataset

- [Example dataset](kto_en_demo.json)
-
-KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
-
-```json
-[
-  {
-    "instruction": "human instruction (required)",
-    "input": "human input (optional)",
-    "output": "model response (required)",
-    "kto_tag": "human feedback [true/false] (required)"
-  }
-]
-```
-
-Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
-
-```json
-"dataset_name": {
-  "file_name": "data.json",
-  "columns": {
-    "prompt": "instruction",
-    "query": "input",
-    "response": "output",
-    "kto_tag": "kto_tag"
-  }
-}
-```
-
-### Multimodal Dataset
+An additional column `kto_tag` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.

- [Example dataset](mllm_demo.json)
+### Multimodal Image Dataset

-Multimodal datasets require a `images` column containing the paths to the input images. Currently we only support one image.
-
-```json
-[
-  {
-    "instruction": "human instruction (required)",
-    "input": "human input (optional)",
-    "output": "model response (required)",
-    "images": [
-      "image path (required)"
-    ]
-  }
-]
-```
+An additional column `images` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.

-Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+### Multimodal Video Dataset

-```json
-"dataset_name": {
-  "file_name": "data.json",
-  "columns": {
-    "prompt": "instruction",
-    "query": "input",
-    "response": "output",
-    "images": "images"
-  }
-}
-```
+An additional column `videos` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.

 ## Sharegpt Format

@@ -252,6 +201,10 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 }
 ```

+### Pre-training Dataset
+
+Not yet supported, please use the [alpaca](#alpaca-format) format.
+
 ### Preference Dataset

 - [Example dataset](dpo_en_demo.json)
@@ -302,6 +255,125 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 }
 ```

+### KTO Dataset
+
+- [Example dataset](kto_en_demo.json)
+
+KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "kto_tag": "human feedback [true/false] (required)"
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+
+### Multimodal Image Dataset
+
+- [Example dataset](mllm_demo.json)
+
+Multimodal image datasets require a `images` column containing the paths to the input images.
+
+The number of images should be identical to the `<image>` tokens in the conversations.
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<image>human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "images": [
+      "image path (required)"
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "images": "images"
+  }
+}
+```
+
+### Multimodal Video Dataset
+
+- [Example dataset](mllm_video_demo.json)
+
+Multimodal video datasets require a `videos` column containing the paths to the input videos.
+
+The number of videos should be identical to the `<video>` tokens in the conversations.
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<video>human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "videos": [
+      "video path (required)"
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "videos": "videos"
+  }
+}
+```
+
 ### OpenAI Format

 The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.
@@ -345,7 +417,3 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
  }
 }
 ```
-
-The KTO datasets and multimodal datasets in sharegpt format are similar to the alpaca format.
-
-Pre-training datasets are **incompatible** with the sharegpt format.
--- a/data/README_zh.md
+++ b/data/README_zh.md
@@ -23,6 +23,7 @@
    "system": "数据集代表系统提示的表头名称（默认：None）",
    "tools": "数据集代表工具描述的表头名称（默认：None）",
    "images": "数据集代表图像输入的表头名称（默认：None）",
+    "videos": "数据集代表视频输入的表头名称（默认：None）",
    "chosen": "数据集代表更优回答的表头名称（默认：None）",
    "rejected": "数据集代表更差回答的表头名称（默认：None）",
    "kto_tag": "数据集代表 KTO 标签的表头名称（默认：None）"
@@ -107,7 +108,7 @@

 ### 偏好数据集

-偏好数据集用于奖励模型训练、DPO 训练和 ORPO 训练。
+偏好数据集用于奖励模型训练、DPO 训练、ORPO 训练和 SimPO 训练。

 它需要在 `chosen` 列中提供更优的回答，并在 `rejected` 列中提供更差的回答。

@@ -139,67 +140,15 @@

 ### KTO 数据集

- [样例数据集](kto_en_demo.json)
-
-KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人类反馈。
-
-```json
-[
-  {
-    "instruction": "人类指令（必填）",
-    "input": "人类输入（选填）",
-    "output": "模型回答（必填）",
-    "kto_tag": "人类反馈 [true/false]（必填）"
-  }
-]
-```
-
-对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
-
-```json
-"数据集名称": {
-  "file_name": "data.json",
-  "columns": {
-    "prompt": "instruction",
-    "query": "input",
-    "response": "output",
-    "kto_tag": "kto_tag"
-  }
-}
-```
-
-### 多模态数据集
+KTO 数据集需要提供额外的 `kto_tag` 列。详情请参阅 [sharegpt](#sharegpt-格式)。

- [样例数据集](mllm_demo.json)
+### 多模态图像数据集

-多模态数据集需要额外添加一个 `images` 列，包含输入图像的路径。目前我们仅支持单张图像输入。
-
-```json
-[
-  {
-    "instruction": "人类指令（必填）",
-    "input": "人类输入（选填）",
-    "output": "模型回答（必填）",
-    "images": [
-      "图像路径（必填）"
-    ]
-  }
-]
-```
+多模态图像数据集需要提供额外的 `images` 列。详情请参阅 [sharegpt](#sharegpt-格式)。

-对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+### 多模态视频数据集

-```json
-"数据集名称": {
-  "file_name": "data.json",
-  "columns": {
-    "prompt": "instruction",
-    "query": "input",
-    "response": "output",
-    "images": "images"
-  }
-}
-```
+多模态视频数据集需要提供额外的 `videos` 列。详情请参阅 [sharegpt](#sharegpt-格式)。

 ## Sharegpt 格式

@@ -252,6 +201,10 @@ KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人
 }
 ```

+### 预训练数据集
+
+尚不支持，请使用 [alpaca](#alpaca-格式) 格式。
+
 ### 偏好数据集

 - [样例数据集](dpo_zh_demo.json)
@@ -302,6 +255,125 @@ Sharegpt 格式的偏好数据集同样需要在 `chosen` 列中提供更优的
 }
 ```

+### KTO 数据集
+
+- [样例数据集](kto_en_demo.json)
+
+KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人类反馈。
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "kto_tag": "人类反馈 [true/false]（必填）"
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+
+### 多模态图像数据集
+
+- [样例数据集](mllm_demo.json)
+
+多模态图像数据集需要额外添加一个 `images` 列，包含输入图像的路径。
+
+注意图片的数量必须与文本中所有 `<image>` 标记的数量严格一致。
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<image>人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "images": [
+      "图像路径（必填）"
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "images": "images"
+  }
+}
+```
+
+### 多模态视频数据集
+
+- [样例数据集](mllm_video_demo.json)
+
+多模态视频数据集需要额外添加一个 `videos` 列，包含输入视频的路径。
+
+注意视频的数量必须与文本中所有 `<video>` 标记的数量严格一致。
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<video>人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "videos": [
+      "视频路径（必填）"
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "videos": "videos"
+  }
+}
+```
+
 ### OpenAI 格式

 OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消息可能是系统提示词。
@@ -345,7 +417,3 @@ OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消
  }
 }
 ```
-
-Sharegpt 格式中的 KTO 数据集和多模态数据集与 alpaca 格式的类似。
-
-预训练数据集**不支持** sharegpt 格式。
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -38,6 +38,20 @@
      "assistant_tag": "assistant"
    }
  },
+  "mllm_video_demo": {
+    "file_name": "mllm_video_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "videos": "videos"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
  "alpaca_en": {
    "hf_hub_url": "llamafactory/alpaca_en",
    "ms_hub_url": "llamafactory/alpaca_en"
@@ -340,6 +354,14 @@
      "assistant_tag": "assistant"
    }
  },
+  "pokemon_cap": {
+    "hf_hub_url": "llamafactory/pokemon-gpt4o-captions",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "images": "images"
+    }
+  },
  "mllm_pt_demo": {
    "hf_hub_url": "BUAADreamer/mllm_pt_demo",
    "formatting": "sharegpt",
@@ -433,6 +455,28 @@
      "rejected": "rejected"
    }
  },
+  "rlhf_v": {
+    "hf_hub_url": "llamafactory/RLHF-V",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected",
+      "images": "images"
+    }
+  },
+  "vlfeedback": {
+    "hf_hub_url": "Zhihui/VLFeedback",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected",
+      "images": "images"
+    }
+  },
  "orca_pairs": {
    "hf_hub_url": "Intel/orca_dpo_pairs",
    "ranking": true,

--- a/data/mllm_demo.json
+++ b/data/mllm_demo.json
@@ -2,7 +2,7 @@
  {
    "messages": [
      {
-        "content": "Who are they?",
+        "content": "<image>Who are they?",
        "role": "user"
      },
      {
@@ -25,7 +25,7 @@
  {
    "messages": [
      {
-        "content": "Who is he?",
+        "content": "<image>Who is he?",
        "role": "user"
      },
      {
@@ -48,7 +48,7 @@
  {
    "messages": [
      {
-        "content": "Please describe this image",
+        "content": "<image>Please describe this image",
        "role": "user"
      },
      {
@@ -71,7 +71,7 @@
  {
    "messages": [
      {
-        "content": "他们是谁？",
+        "content": "<image>他们是谁？",
        "role": "user"
      },
      {
@@ -94,7 +94,7 @@
  {
    "messages": [
      {
-        "content": "他是谁？",
+        "content": "<image>他是谁？",
        "role": "user"
      },
      {
@@ -117,7 +117,7 @@
  {
    "messages": [
      {
-        "content": "请描述这张图片",
+        "content": "<image>请描述这张图片",
        "role": "user"
      },
      {

--- a/data/mllm_demo_data/1.mp4
+++ b/data/mllm_demo_data/1.mp4
--- a/data/mllm_demo_data/2.avi
+++ b/data/mllm_demo_data/2.avi
--- a/data/mllm_demo_data/3.mp4
+++ b/data/mllm_demo_data/3.mp4
--- a/data/mllm_video_demo.json
+++ b/data/mllm_video_demo.json
+[
+  {
+    "messages": [
+      {
+        "content": "<video>Why is this video funny?",
+        "role": "user"
+      },
+      {
+        "content": "Because a baby is reading, and he is so cute!",
+        "role": "assistant"
+      }
+    ],
+    "videos": [
+      "mllm_demo_data/1.mp4"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "<video>What is she doing?",
+        "role": "user"
+      },
+      {
+        "content": "She is cooking.",
+        "role": "assistant"
+      }
+    ],
+    "videos": [
+      "mllm_demo_data/2.avi"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "<video>What's in the video?",
+        "role": "user"
+      },
+      {
+        "content": "A baby is playing in the living room.",
+        "role": "assistant"
+      }
+    ],
+    "videos": [
+      "mllm_demo_data/3.mp4"
+    ]
+  }
+]
\ No newline at end of file
--- a/docker/docker-cuda/Dockerfile
+++ b/docker/docker-cuda/Dockerfile
+# Use the NVIDIA official image with PyTorch 2.3.0
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-02.html
+FROM nvcr.io/nvidia/pytorch:24.02-py3
+
+# Define environments
+ENV MAX_JOBS=4
+ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+# Define installation arguments
+ARG INSTALL_BNB=false
+ARG INSTALL_VLLM=false
+ARG INSTALL_DEEPSPEED=false
+ARG INSTALL_FLASHATTN=false
+ARG INSTALL_LIGER_KERNEL=false
+ARG INSTALL_HQQ=false
+ARG INSTALL_EETQ=false
+ARG PIP_INDEX=https://pypi.org/simple
+
+# Set the working directory
+WORKDIR /app
+
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$PIP_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+
+# Copy the rest of the application into the image
+COPY . /app
+
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="metrics"; \
+    if [ "$INSTALL_BNB" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
+    fi; \
+    if [ "$INSTALL_VLLM" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
+    fi; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
+    fi; \
+    if [ "$INSTALL_HQQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
+    fi; \
+    if [ "$INSTALL_EETQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},eetq"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+
+# Rebuild flash attention
+RUN pip uninstall -y transformer-engine flash-attn && \
+    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
+        pip uninstall -y ninja && pip install ninja && \
+        pip install --no-cache-dir flash-attn --no-build-isolation; \
+    fi
+
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
--- a/docker/docker-cuda/docker-compose.yml
+++ b/docker/docker-cuda/docker-compose.yml
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-cuda/Dockerfile
+      context: ../..
+      args:
+        INSTALL_BNB: false
+        INSTALL_VLLM: false
+        INSTALL_DEEPSPEED: false
+        INSTALL_FLASHATTN: false
+        INSTALL_LIGER_KERNEL: false
+        INSTALL_HQQ: false
+        INSTALL_EETQ: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../data:/app/data
+      - ../../output:/app/output
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: "all"
+            capabilities: [gpu]
+    restart: unless-stopped
--- a/docker/docker-npu/Dockerfile
+++ b/docker/docker-npu/Dockerfile
+# Use the Ubuntu 22.04 image with CANN 8.0.rc1
+# More versions can be found at https://hub.docker.com/r/ascendai/cann/tags
+# FROM ascendai/cann:8.0.rc1-910-ubuntu22.04-py3.8
+FROM ascendai/cann:8.0.rc1-910b-ubuntu22.04-py3.8
+# FROM ascendai/cann:8.0.rc1-910-openeuler22.03-py3.8
+# FROM ascendai/cann:8.0.rc1-910b-openeuler22.03-py3.8
+
+# Define environments
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Define installation arguments
+ARG INSTALL_DEEPSPEED=false
+ARG PIP_INDEX=https://pypi.org/simple
+ARG TORCH_INDEX=https://download.pytorch.org/whl/cpu
+
+# Set the working directory
+WORKDIR /app
+
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$TORCH_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+
+# Copy the rest of the application into the image
+COPY . /app
+
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="torch-npu,metrics"; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
--- a/docker/docker-npu/docker-compose.yml
+++ b/docker/docker-npu/docker-compose.yml
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-npu/Dockerfile
+      context: ../..
+      args:
+        INSTALL_DEEPSPEED: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../data:/app/data
+      - ../../output:/app/output
+      - /usr/local/dcmi:/usr/local/dcmi
+      - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
+      - /usr/local/Ascend/driver:/usr/local/Ascend/driver
+      - /etc/ascend_install.info:/etc/ascend_install.info
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    devices:
+      - /dev/davinci0
+      - /dev/davinci_manager
+      - /dev/devmm_svm
+      - /dev/hisi_hdc
+    restart: unless-stopped
--- a/docker/docker-rocm/Dockerfile
+++ b/docker/docker-rocm/Dockerfile
+FROM hardandheavy/transformers-rocm:2.2.0
+
+# Define environments
+ENV MAX_JOBS=4
+ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+# Define installation arguments
+ARG INSTALL_BNB=false
+ARG INSTALL_VLLM=false
+ARG INSTALL_DEEPSPEED=false
+ARG INSTALL_FLASHATTN=false
+ARG INSTALL_LIGER_KERNEL=false
+ARG INSTALL_HQQ=false
+ARG PIP_INDEX=https://pypi.org/simple
+
+# Set the working directory
+WORKDIR /app
+
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$PIP_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+
+# Copy the rest of the application into the image
+COPY . /app
+
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="metrics"; \
+    if [ "$INSTALL_BNB" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
+    fi; \
+    if [ "$INSTALL_VLLM" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
+    fi; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
+    fi; \
+    if [ "$INSTALL_HQQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+
+# Rebuild flash attention
+RUN pip uninstall -y transformer-engine flash-attn && \
+    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
+        pip uninstall -y ninja && pip install ninja && \
+        pip install --no-cache-dir flash-attn --no-build-isolation; \
+    fi
+
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
--- a/docker/docker-rocm/docker-compose.yml
+++ b/docker/docker-rocm/docker-compose.yml
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-rocm/Dockerfile
+      context: ../..
+      args:
+        INSTALL_BNB: false
+        INSTALL_VLLM: false
+        INSTALL_DEEPSPEED: false
+        INSTALL_FLASHATTN: false
+        INSTALL_LIGER_KERNEL: false
+        INSTALL_HQQ: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../data:/app/data
+      - ../../output:/app/output
+      - ../../saves:/app/saves
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    restart: unless-stopped