Add QWQ-32B

317a82e2 · chenych · 37b0ad9f · 317a82e2 · 317a82e2 · 317a82e2
Commit 317a82e2 authored Mar 07, 2025 by chenych
20 changed files
--- a/.env.local
+++ b/.env.local
@@ -4,11 +4,13 @@ API_HOST=
 API_PORT=
 API_KEY=
 API_MODEL_NAME=
+API_VERBOSE=
 FASTAPI_ROOT_PATH=
 MAX_CONCURRENT=
 # general
 DISABLE_VERSION_CHECK=
 FORCE_CHECK_IMPORTS=
+ALLOW_EXTRA_ARGS=
 LLAMAFACTORY_VERBOSITY=
 USE_MODELSCOPE_HUB=
 USE_OPENMIND_HUB=
@@ -32,7 +34,7 @@ GRADIO_SERVER_PORT=
 GRADIO_ROOT_PATH=
 GRADIO_IPV6=
 # setup
-ENABLE_SHORT_CONSOLE=1
+ENABLE_SHORT_CONSOLE=
 # reserved (do not use)
 LLAMABOARD_ENABLED=
 LLAMABOARD_WORKDIR=
--- a/.gitignore
+++ b/.gitignore
@@ -162,6 +162,9 @@ cython_debug/
 # vscode
 .vscode/
+# uv
+uv.lock
 # custom .gitignore
 ms_cache/
 hf_cache/

--- a/README.md
+++ b/README.md
@@ -15,6 +15,7 @@ LLaMA Factory是一个大语言模型训练和推理的框架，支持了魔搭
 ## 支持模型结构列表
 | 模型名                                                       | 模型大小                          | Template  |
 | ------------------------------------------------------------ | -------------------------------- | --------- |
 | [Baichuan 2](https://huggingface.co/baichuan-inc)            | 7B/13B                           | baichuan2 |
@@ -23,11 +24,10 @@ LLaMA Factory是一个大语言模型训练和推理的框架，支持了魔搭
 | [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/Qwen2.5](https://huggingface.co/Qwen)            | 0.5B/1.8B/4B/7B/14B/32B/72B      | qwen      |
+| [Qwen1.5 (Code/MoE)/Qwen2/Qwen2.5/QwQ](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      |
 持续更新中...
 注意：本版本仅支持deepseek蒸馏模型的监督微调(SFT)，可参考[deepseek-r1-distill_vllm](https://developer.sourcefind.cn/codes/modelzoo/deepseek-r1-distill_vllm)

--- a/README_en.md
+++ b/README_en.md
 ![# LLaMA Factory](assets/logo.png)
 [![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Factory?style=social)](https://github.com/hiyouga/LLaMA-Factory/stargazers)
-[![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Factory)](LICENSE)
 [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main)
+[![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors)
+[![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml)
 [![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)
+[![Citation](https://img.shields.io/badge/citation-319-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
 [![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)
+[![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK)
+[![GitCode](https://gitcode.com/zhengyaowei/LLaMA-Factory/star/badge.svg)](https://gitcode.com/zhengyaowei/LLaMA-Factory)
 [![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)
+[![SageMaker](https://img.shields.io/badge/SageMaker-Open%20in%20AWS-blue)](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)
-[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)
+<h3 align="center">
+    Easily fine-tune 100+ large language models with zero-code <a href="#quickstart">CLI</a> and <a href="#fine-tuning-with-llama-board-gui-powered-by-gradio">Web UI</a>
+</h3>
+<p align="center">
+    <picture>
+        <img alt="Github trend" src="https://trendshift.io/api/badge/repositories/4535">
+    </picture>
+</p>
 👋 Join our [WeChat](assets/wechat.jpg) or [NPU user group](assets/wechat_npu.jpg).
@@ -25,10 +37,11 @@ https://github.com/user-attachments/assets/7c96b465-9df7-45f4-8053-bf03e58386d3
 Choose your path:
+- **Documentation (WIP)**: https://llamafactory.readthedocs.io/zh-cn/latest/
 - **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/
+- **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) | [DeepSeek-R1-Distill Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b)
+- **Amazon SageMaker**: [Blog](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)
 > [!NOTE]
 > Except for the above links, all other websites are unauthorized third-party websites. Please carefully use them.
@@ -43,6 +56,16 @@ Choose your path:
 - [Provided Datasets](#provided-datasets)
 - [Requirement](#requirement)
 - [Getting Started](#getting-started)
+  - [Installation](#installation)
+  - [Data Preparation](#data-preparation)
+  - [Quickstart](#quickstart)
+  - [Fine-Tuning with LLaMA Board GUI](#fine-tuning-with-llama-board-gui-powered-by-gradio)
+  - [Build Docker](#build-docker)
+  - [Deploy with OpenAI-style API and vLLM](#deploy-with-openai-style-api-and-vllm)
+  - [Download from ModelScope Hub](#download-from-modelscope-hub)
+  - [Download from Modelers Hub](#download-from-modelers-hub)
+  - [Use W&B Logger](#use-wb-logger)
+  - [Use SwanLab Logger](#use-swanlab-logger)
 - [Projects using LLaMA Factory](#projects-using-llama-factory)
 - [License](#license)
 - [Citation](#citation)
@@ -50,14 +73,22 @@ Choose your path:
 ## Features
- **Various models**: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Qwen2-VL, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.
+- **Various models**: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Qwen2-VL, DeepSeek, Yi, Gemma, 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.
+- **Advanced algorithms**: [GaLore](https://github.com/jiaweizzhao/GaLore), [BAdam](https://github.com/Ledzy/BAdam), [APOLLO](https://github.com/zhuhanqing/APOLLO), [Adam-mini](https://github.com/zyushun/Adam-mini), DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ and PiSSA.
 - **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.
+- **Wide tasks**: Multi-turn dialogue, tool using, image understanding, visual grounding, video recognition, audio understanding, etc.
+- **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, SwanLab, etc.
 - **Faster inference**: OpenAI-style API, Gradio UI and CLI with vLLM worker.
+### Day-N Support for Fine-Tuning Cutting-Edge Models
+| Support Date | Model Name                                                 |
+| ------------ | ---------------------------------------------------------- |
+| Day 0        | Qwen2.5 / Qwen2-VL / QwQ / QvQ / InternLM3 / MiniCPM-o-2.6 |
+| Day 1        | Llama 3 / GLM-4 / Mistral Small / PaliGemma2               |
 ## 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.
@@ -75,19 +106,41 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 ## Changelog
-[24/09/19] We support fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models.
+[25/02/24] Announcing **[EasyR1](https://github.com/hiyouga/EasyR1)**, an efficient, scalable and multi-modality RL training framework for efficient GRPO training.
-[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.
+[25/02/11] We supported saving the **[Ollama](https://github.com/ollama/ollama)** modelfile when exporting the model checkpoints. See [examples](examples/README.md) for usage.
-[24/08/27] We support **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**. Try `enable_liger_kernel: true` for efficient training.
+[25/02/05] We supported fine-tuning the **[Qwen2-Audio](Qwen/Qwen2-Audio-7B-Instruct)** and **[MiniCPM-o-2.6](https://huggingface.co/openbmb/MiniCPM-o-2_6)** on audio understanding tasks.
-[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.
+[25/01/31] We supported fine-tuning the **[DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)** and **[Qwen2.5-VL](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)** model.
 <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.
+[25/01/15] We supported **[APOLLO](https://arxiv.org/abs/2412.05270)** optimizer. See [examples](examples/README.md) for usage.
+[25/01/14] We supported fine-tuning the **[MiniCPM-o-2.6](https://huggingface.co/openbmb/MiniCPM-o-2_6)** and **[MiniCPM-V-2.6](https://huggingface.co/openbmb/MiniCPM-V-2_6)** models. Thank [@BUAADreamer](https://github.com/BUAADreamer)'s PR.
+[25/01/14] We supported fine-tuning the **[InternLM3](https://huggingface.co/collections/internlm/)** models. Thank [@hhaAndroid](https://github.com/hhaAndroid)'s PR.
+[25/01/10] We supported fine-tuning the **[Phi-4](https://huggingface.co/microsoft/phi-4)** model.
+[24/12/21] We supported using **[SwanLab](https://github.com/SwanHubX/SwanLab)** for experiment tracking and visualization. See [this section](#use-swanlab-logger) for details.
+[24/11/27] We supported fine-tuning the **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** model and the **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** dataset.
+[24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)**. See [this tutorial](#download-from-modelers-hub) for usage.
+[24/09/19] We supported fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models.
+[24/08/30] We supported fine-tuning the **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** models. Thank [@simonJJJ](https://github.com/simonJJJ)'s PR.
-[24/06/16] We support **[PiSSA](https://arxiv.org/abs/2404.02948)** algorithm. See [examples](examples/README.md) for usage.
+[24/08/27] We supported **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**. Try `enable_liger_kernel: true` for efficient training.
+[24/08/09] We supported **[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.
+[24/07/04] We supported [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 supported **[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.
@@ -133,7 +186,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 [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.
+[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)**. 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.
@@ -166,31 +219,46 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 ## 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            |
+| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai)              | 236B/671B                        | deepseek3           |
+| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai)       | 1.5B/7B/8B/14B/32B/70B/671B      | deepseek3           |
 | [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          |
+| [GPT-2](https://huggingface.co/openai-community)                  | 0.1B/0.4B/0.8B/1.5B              | -                   |
+| [Granite 3.0-3.1](https://huggingface.co/ibm-granite)             | 1B/2B/3B/8B                      | granite3            |
+| [Index](https://huggingface.co/IndexTeam)                         | 1.9B                             | index               |
+| [InternLM 2-3](https://huggingface.co/internlm)                   | 7B/8B/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           |
+| [Llama 3-3.3](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3              |
+| [Llama 3.2 Vision](https://huggingface.co/meta-llama)             | 11B/90B                          | mllama              |
 | [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            |
+| [MiniCPM-o-2.6/MiniCPM-V-2.6](https://huggingface.co/openbmb)     | 8B                               | minicpm_o/minicpm_v |
+| [Ministral/Mistral-Nemo](https://huggingface.co/mistralai)        | 8B/12B                           | ministral           |
 | [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral             |
+| [Mistral Small](https://huggingface.co/mistralai)                 | 24B                              | mistral_small       |
 | [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                   |
-| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma        |
+| [PaliGemma/PaliGemma2](https://huggingface.co/google)             | 3B/10B/28B                       | paligemma           |
 | [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                   |
-| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi              |
+| [Phi-3/Phi-3.5](https://huggingface.co/microsoft)                 | 4B/14B                           | phi                 |
-| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
+| [Phi-3-small](https://huggingface.co/microsoft)                   | 7B                               | phi_small           |
-| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl         |
+| [Phi-4](https://huggingface.co/microsoft)                         | 14B                              | phi4                |
+| [Pixtral](https://huggingface.co/mistralai)                       | 12B                              | pixtral             |
+| [Qwen/QwQ (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)   | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen                |
+| [Qwen2-Audio](https://huggingface.co/Qwen)                        | 7B                               | qwen2_audio         |
+| [Qwen2-VL/Qwen2.5-VL/QVQ](https://huggingface.co/Qwen)            | 2B/3B/7B/72B                     | qwen2_vl            |
+| [Skywork o1](https://huggingface.co/Skywork)                      | 8B                               | skywork_o1          |
 | [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                   |
+| [TeleChat2](https://huggingface.co/Tele-AI)                       | 3B/7B/35B/115B                   | telechat2           |
 | [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               |
@@ -278,9 +346,13 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [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)
+- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
+- [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)
+- [Open-Thoughts (en)](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+- [Open-R1-Math (en)](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k)
+- [Chinese-DeepSeek-R1-Distill (zh)](https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT)
 - [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)
@@ -320,32 +392,32 @@ huggingface-cli login
 | Mandatory    | Minimum | Recommend |
 | ------------ | ------- | --------- |
-| python       | 3.8     | 3.11      |
+| python       | 3.9     | 3.10      |
-| torch        | 1.13.1  | 2.4.0     |
+| torch        | 1.13.1  | 2.5.1     |
-| transformers | 4.41.2  | 4.43.4    |
+| transformers | 4.41.2  | 4.49.0    |
-| datasets     | 2.16.0  | 2.20.0    |
+| datasets     | 2.16.0  | 3.2.0     |
-| accelerate   | 0.30.1  | 0.32.0    |
+| accelerate   | 0.34.0  | 1.2.1     |
 | peft         | 0.11.1  | 0.12.0    |
 | trl          | 0.8.6   | 0.9.6     |
 | Optional     | Minimum | Recommend |
 | ------------ | ------- | --------- |
 | CUDA         | 11.6    | 12.2      |
-| deepspeed    | 0.10.0  | 0.14.0    |
+| deepspeed    | 0.10.0  | 0.16.2    |
 | bitsandbytes | 0.39.0  | 0.43.1    |
-| vllm         | 0.4.3   | 0.5.0     |
+| vllm         | 0.4.3   | 0.7.3     |
-| flash-attn   | 2.3.0   | 2.6.3     |
+| flash-attn   | 2.3.0   | 2.7.2     |
 ### Hardware Requirement
 \* *estimated*
 | Method                   | Bits |   7B  |  13B  |  30B  |   70B  |  110B  |  8x7B |  8x22B |
-| ----------------- | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
+| ------------------------ | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
-| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 2000GB | 900GB | 2400GB |
+| Full                     |  32  | 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 |
+| LoRA/GaLore/APOLLO/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 |
@@ -363,36 +435,56 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
-Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, quality
+Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, apollo, badam, adam-mini, qwen, minicpm_v, modelscope, openmind, swanlab, quality
 > [!TIP]
 > Use `pip install --no-deps -e .` to resolve package conflicts.
+<details><summary>Setting up a virtual environment with <b>uv</b></summary>
+Create an isolated Python environment with [uv](https://github.com/astral-sh/uv):
+```bash
+uv sync --extra torch --extra metrics --prerelease=allow
+```
+Run LLaMA-Factory in the isolated environment:
+```bash
+uv run --prerelease=allow llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
+```
+</details>
 <details><summary>For Windows users</summary>
+#### Install BitsAndBytes
 If you want to enable the quantized LoRA (QLoRA) on the Windows platform, you need to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.2, please select the appropriate [release version](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels) based on your CUDA version.
 ```bash
 pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.2.post2-py3-none-win_amd64.whl
 ```
-To enable FlashAttention-2 on the Windows platform, you need to install the precompiled `flash-attn` library, which supports CUDA 12.1 to 12.2. Please download the corresponding version from [flash-attention](https://github.com/bdashore3/flash-attention/releases) based on your requirements.
+#### Install Flash Attention-2
+To enable FlashAttention-2 on the Windows platform, please use the script from [flash-attention-windows-wheel](https://huggingface.co/lldacing/flash-attention-windows-wheel) to compile and install it by yourself.
 </details>
 <details><summary>For Ascend NPU users</summary>
-To install LLaMA Factory on Ascend NPU devices, please specify extra dependencies: `pip install -e ".[torch-npu,metrics]"`. Additionally, you need to install the **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**. Please follow the [installation tutorial](https://www.hiascend.com/document/detail/en/CANNCommunityEdition/600alphaX/softwareinstall/instg/atlasdeploy_03_0031.html) or use the following commands:
+To install LLaMA Factory on Ascend NPU devices, please upgrade Python to version 3.10 or higher and 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-"$(uname -i)".run
+wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C20SPC702/Ascend-cann-toolkit_8.0.0.alpha002_linux-"$(uname -i)".run
-bash Ascend-cann-toolkit_8.0.RC1.alpha001_linux-"$(uname -i)".run --install
+bash Ascend-cann-toolkit_8.0.0.alpha002_linux-"$(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
+wget https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C20SPC702/Ascend-cann-kernels-910b_8.0.0.alpha002_linux-"$(uname -i)".run
-bash Ascend-cann-kernels-910b_8.0.RC1.alpha001_linux.run --install
+bash Ascend-cann-kernels-910b_8.0.0.alpha002_linux-"$(uname -i)".run --install
 # set env variables
 source /usr/local/Ascend/ascend-toolkit/set_env.sh
@@ -400,10 +492,10 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | Requirement  | Minimum | Recommend   |
 | ------------ | ------- | ----------- |
-| CANN         | 8.0.RC1 | 8.0.RC1     |
+| CANN         | 8.0.RC1 | 8.0.0.alpha002     |
-| torch        | 2.1.0   | 2.1.0       |
+| torch        | 2.1.0   | 2.4.0      |
-| torch-npu    | 2.1.0   | 2.1.0.post3 |
+| torch-npu    | 2.1.0   | 2.4.0.post2 |
-| deepspeed    | 0.13.2  | 0.13.2      |
+| deepspeed    | 0.13.2  | 0.16.2     |
 Remember to use `ASCEND_RT_VISIBLE_DEVICES` instead of `CUDA_VISIBLE_DEVICES` to specify the device to use.
@@ -411,11 +503,45 @@ If you cannot infer model on NPU devices, try setting `do_sample: false` in the
 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)
+#### Install BitsAndBytes
+To use QLoRA based on bitsandbytes on Ascend NPU, please follow these 3 steps:
+1. Manually compile bitsandbytes: Refer to [the installation documentation](https://huggingface.co/docs/bitsandbytes/installation?backend=Ascend+NPU&platform=Ascend+NPU) for the NPU version of bitsandbytes to complete the compilation and installation. The compilation requires a cmake version of at least 3.22.1 and a g++ version of at least 12.x.
+```bash
+# Install bitsandbytes from source
+# Clone bitsandbytes repo, Ascend NPU backend is currently enabled on multi-backend-refactor branch
+git clone -b multi-backend-refactor https://github.com/bitsandbytes-foundation/bitsandbytes.git
+cd bitsandbytes/
+# Install dependencies
+pip install -r requirements-dev.txt
+# Install the dependencies for the compilation tools. Note that the commands for this step may vary depending on the operating system. The following are provided for reference
+apt-get install -y build-essential cmake
+# Compile & install  
+cmake -DCOMPUTE_BACKEND=npu -S .
+make
+pip install .
+```
+2. Install transformers from the main branch.
+```bash
+git clone -b main https://github.com/huggingface/transformers.git
+cd transformers
+pip install .
+```
+3. Set `double_quantization: false` in the configuration. You can refer to the [example](examples/train_qlora/llama3_lora_sft_bnb_npu.yaml).
 </details>
 ### Data Preparation
-Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope hub or load the dataset in local disk.
+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 / Modelers hub or load the dataset in local disk.
 > [!NOTE]
 > Please update `data/dataset_info.json` to use your custom dataset.
@@ -483,6 +609,7 @@ docker build -f ./docker/docker-cuda/Dockerfile \
 docker run -dit --gpus=all \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -p 7860:7860 \
@@ -507,6 +634,7 @@ docker build -f ./docker/docker-npu/Dockerfile \
 docker run -dit \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -v /usr/local/dcmi:/usr/local/dcmi \
@@ -540,6 +668,7 @@ docker build -f ./docker/docker-rocm/Dockerfile \
 docker run -dit \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -v ./saves:/app/saves \
@@ -560,6 +689,7 @@ docker exec -it llamafactory bash
 - `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.
+- `om_cache`: Similar to Hugging Face cache but for Modelers 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.
@@ -573,6 +703,8 @@ API_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml
 > [!TIP]
 > Visit [this page](https://platform.openai.com/docs/api-reference/chat/create) for API document.
+>
+> Examples: [Image understanding](scripts/api_example/test_image.py) | [Function calling](scripts/api_example/test_toolcall.py)
 ### Download from ModelScope Hub
@@ -584,6 +716,16 @@ 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`.
+### Download from Modelers Hub
+You can also use Modelers Hub to download models and datasets.
+```bash
+export USE_OPENMIND_HUB=1 # `set USE_OPENMIND_HUB=1` for Windows
+```
+Train the model by specifying a model ID of the Modelers Hub as the `model_name_or_path`. You can find a full list of model IDs at [Modelers Hub](https://modelers.cn/models), e.g., `TeleAI/TeleChat-7B-pt`.
 ### 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.
@@ -595,6 +737,21 @@ 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.
+### Use SwanLab Logger
+To use [SwanLab](https://github.com/SwanHubX/SwanLab) for logging experimental results, you need to add the following arguments to yaml files.
+```yaml
+use_swanlab: true
+swanlab_run_name: test_run # optional
+```
+When launching training tasks, you can log in to SwanLab in three ways:
+1. Add `swanlab_api_key=<your_api_key>` to the yaml file, and set it to your [API key](https://swanlab.cn/settings).
+2. Set the environment variable `SWANLAB_API_KEY` to your [API key](https://swanlab.cn/settings).
+3. Use the `swanlab login` command to complete the login.
 ## Projects using LLaMA Factory
 If you have a project that should be incorporated, please contact via email or create a pull request.
@@ -682,16 +839,20 @@ If you have a project that should be incorporated, please contact via email or c
 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. Bai et al. Aligning Large Language Model with Direct Multi-Preference Optimization for Recommendation. CIKM 2024. [[paper]](https://dl.acm.org/doi/10.1145/3627673.3679611)
 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. **[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.
+1. **[RAG-Retrieval](https://github.com/NLPJCL/RAG-Retrieval)**: A full pipeline for RAG retrieval model fine-tuning, inference, and distillation. [[blog]](https://zhuanlan.zhihu.com/p/987727357)
+1. **[360-LLaMA-Factory](https://github.com/Qihoo360/360-LLaMA-Factory)**: A modified library that supports long sequence SFT & DPO using ring attention.
+1. **[Sky-T1](https://novasky-ai.github.io/posts/sky-t1/)**: An o1-like model fine-tuned by NovaSky AI with very small cost.
 </details>
@@ -699,7 +860,7 @@ If you have a project that should be incorporated, please contact via email or c
 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)
+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) / [GPT-2](https://github.com/openai/gpt-2/blob/master/LICENSE) / [Granite](LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM](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/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3/Phi-4](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [Skywork](https://huggingface.co/Skywork/Skywork-13B-base/blob/main/Skywork%20Community%20License.pdf) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [TeleChat2](https://huggingface.co/Tele-AI/telechat-7B/blob/main/TeleChat%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf) / [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

--- a/README_zh.md
+++ b/README_zh.md
 ![# LLaMA Factory](assets/logo.png)
 [![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Factory?style=social)](https://github.com/hiyouga/LLaMA-Factory/stargazers)
-[![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Factory)](LICENSE)
 [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main)
+[![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors)
+[![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml)
 [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
-[![Citation](https://img.shields.io/badge/citation-91-green)](#使用了-llama-factory-的项目)
+[![Citation](https://img.shields.io/badge/citation-319-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
 [![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)
+[![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK)
+[![GitCode](https://gitcode.com/zhengyaowei/LLaMA-Factory/star/badge.svg)](https://gitcode.com/zhengyaowei/LLaMA-Factory)
 [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?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)
+[![SageMaker](https://img.shields.io/badge/SageMaker-Open%20in%20AWS-blue)](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)
+<h3 align="center">
+    使用零代码<a href="#快速开始">命令行</a>与 <a href="#llama-board-可视化微调由-gradio-驱动">Web UI</a> 轻松微调百余种大模型
+</h3>
+<p align="center">
+    <picture>
+        <img alt="Github trend" src="https://trendshift.io/api/badge/repositories/4535">
+    </picture>
+</p>
-[![GitHub Tread](https://trendshift.io/api/badge/repositories/4535)](https://trendshift.io/repositories/4535)
 👋 加入我们的[微信群](assets/wechat.jpg)或 [NPU 用户群](assets/wechat_npu.jpg)。
@@ -25,11 +38,12 @@ 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**：[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/
+- **Colab**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing
+- **本地机器**：请见[如何使用](#如何使用)
+- **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) | [DeepSeek-R1-Distill 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b)
+- **Amazon SageMaker**：[博客](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)
 > [!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。
@@ -44,6 +58,16 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [数据集](#数据集)
 - [软硬件依赖](#软硬件依赖)
 - [如何使用](#如何使用)
+  - [安装 LLaMA Factory](#安装-llama-factory)
+  - [数据准备](#数据准备)
+  - [快速开始](#快速开始)
+  - [LLaMA Board 可视化微调](#llama-board-可视化微调由-gradio-驱动)
+  - [构建 Docker](#构建-docker)
+  - [利用 vLLM 部署 OpenAI API](#利用-vllm-部署-openai-api)
+  - [从魔搭社区下载](#从魔搭社区下载)
+  - [从魔乐社区下载](#从魔乐社区下载)
+  - [使用 W&B 面板](#使用-wb-面板)
+  - [使用 SwanLab 面板](#使用-swanlab-面板)
 - [使用了 LLaMA Factory 的项目](#使用了-llama-factory-的项目)
 - [协议](#协议)
 - [引用](#引用)
@@ -51,14 +75,22 @@ 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、Qwen2-VL、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
+- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Qwen2-VL、DeepSeek、Yi、Gemma、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](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。
+- **先进算法**：[GaLore](https://github.com/jiaweizzhao/GaLore)、[BAdam](https://github.com/Ledzy/BAdam)、[APOLLO](https://github.com/zhuhanqing/APOLLO)、[Adam-mini](https://github.com/zyushun/Adam-mini)、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ 和 PiSSA。
 - **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。
+- **广泛任务**：多轮对话、工具调用、图像理解、视觉定位、视频识别和语音理解等等。
+- **实验监控**：LlamaBoard、TensorBoard、Wandb、MLflow、SwanLab 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。
+### 最新模型的 Day-N 微调适配
+| 适配时间      | 模型名称                                                    |
+| ------------ | ---------------------------------------------------------- |
+| Day 0        | Qwen2.5 / Qwen2-VL / QwQ / QvQ / InternLM3 / MiniCPM-o-2.6 |
+| Day 1        | Llama 3 / GLM-4 / Mistral Small / PaliGemma2               |
 ## 性能指标
 与 ChatGLM 官方的 [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ptuning) 微调相比，LLaMA Factory 的 LoRA 微调提供了 **3.7 倍**的加速比，同时在广告文案生成任务上取得了更高的 Rouge 分数。结合 4 比特量化技术，LLaMA Factory 的 QLoRA 微调进一步降低了 GPU 显存消耗。
@@ -76,6 +108,30 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 ## 更新日志
+[25/02/24] 我们宣布开源 **[EasyR1](https://github.com/hiyouga/EasyR1)**，一个高效可扩展的多模态强化学习框架，支持高效的 GRPO 训练。
+[25/02/11] 我们支持了在导出模型时保存 **[Ollama](https://github.com/ollama/ollama)** 配置文件。详细用法请参照 [examples](examples/README_zh.md)。
+[25/02/05] 我们支持了在语音理解任务上微调 **[Qwen2-Audio](Qwen/Qwen2-Audio-7B-Instruct)** 和 **[MiniCPM-o-2.6](https://huggingface.co/openbmb/MiniCPM-o-2_6)** 模型。
+[25/01/31] 我们支持了 **[DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)** 和 **[Qwen2.5-VL](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)** 模型的微调。
+<details><summary>展开日志</summary>
+[25/01/15] 我们支持了 **[APOLLO](https://arxiv.org/abs/2412.05270)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。
+[25/01/14] 我们支持了 **[MiniCPM-o-2.6](https://huggingface.co/openbmb/MiniCPM-o-2_6)** 和 **[MiniCPM-V-2.6](https://huggingface.co/openbmb/MiniCPM-V-2_6)** 模型的微调。 感谢 [@BUAADreamer](https://github.com/BUAADreamer) 的 PR.
+[25/01/14] 我们支持了 **[InternLM3](https://huggingface.co/collections/internlm/)** 模型的微调。感谢 [@hhaAndroid](https://github.com/hhaAndroid) 的 PR。
+[25/01/10] 我们支持了 **[Phi-4](https://huggingface.co/microsoft/phi-4)** 模型的微调。
+[24/12/21] 我们支持了使用 **[SwanLab](https://github.com/SwanHubX/SwanLab)** 跟踪与可视化实验。详细用法请参考 [此部分](#使用-swanlab-面板)。
+[24/11/27] 我们支持了 **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** 模型的微调和 **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** 数据集。
+[24/10/09] 我们支持了从 **[魔乐社区](https://modelers.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔乐社区下载)。
 [24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。
 [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。
@@ -84,8 +140,6 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 [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)。
@@ -166,32 +220,47 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 ## 模型
-| 模型名                                                            | 模型大小                          | Template         |
+| 模型名                                                             | 参数量                            | 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            |
+| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai)              | 236B/671B                        | deepseek3           |
+| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai)       | 1.5B/7B/8B/14B/32B/70B/671B      | deepseek3           |
 | [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          |
+| [GPT-2](https://huggingface.co/openai-community)                  | 0.1B/0.4B/0.8B/1.5B              | -                   |
+| [Granite 3.0-3.1](https://huggingface.co/ibm-granite)             | 1B/2B/3B/8B                      | granite3            |
+| [Index](https://huggingface.co/IndexTeam)                         | 1.9B                             | index               |
+| [InternLM 2-3](https://huggingface.co/internlm)                   | 7B/8B/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           |
+| [Llama 3-3.3](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3              |
+| [Llama 3.2 Vision](https://huggingface.co/meta-llama)             | 11B/90B                          | mllama              |
 | [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            |
+| [MiniCPM-o-2.6/MiniCPM-V-2.6](https://huggingface.co/openbmb)     | 8B                               | minicpm_o/minicpm_v |
+| [Ministral/Mistral-Nemo](https://huggingface.co/mistralai)        | 8B/12B                           | ministral           |
 | [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral             |
+| [Mistral Small](https://huggingface.co/mistralai)                 | 24B                              | mistral_small       |
 | [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                   |
-| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma        |
+| [PaliGemma/PaliGemma2](https://huggingface.co/google)             | 3B/10B/28B                       | paligemma           |
 | [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                   |
-| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi              |
+| [Phi-3/Phi-3.5](https://huggingface.co/microsoft)                 | 4B/14B                           | phi                 |
-| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
+| [Phi-3-small](https://huggingface.co/microsoft)                   | 7B                               | phi_small           |
-| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl         |
+| [Phi-4](https://huggingface.co/microsoft)                         | 14B                              | phi4                |
+| [Pixtral](https://huggingface.co/mistralai)                       | 12B                              | pixtral             |
+| [Qwen/QwQ (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)   | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen                |
+| [Qwen2-Audio](https://huggingface.co/Qwen)                        | 7B                               | qwen2_audio         |
+| [Qwen2-VL/Qwen2.5-VL/QVQ](https://huggingface.co/Qwen)            | 2B/3B/7B/72B                     | qwen2_vl            |
+| [Skywork o1](https://huggingface.co/Skywork)                      | 8B                               | skywork_o1          |
 | [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                   |
+| [TeleChat2](https://huggingface.co/Tele-AI)                       | 3B/7B/35B/115B                   | telechat2           |
 | [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               |
@@ -209,7 +278,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 ## 训练方法
 | 方法                   |     全参数训练      |    部分参数训练     |       LoRA         |       QLoRA        |
-| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ |
+| --------------------- | ------------------ | ------------------ | ------------------ | ------------------ |
 | 预训练                 | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | 指令监督微调            | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
 | 奖励模型训练            | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
@@ -279,9 +348,13 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [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)
+- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
+- [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)
+- [Open-Thoughts (en)](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+- [Open-R1-Math (en)](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k)
+- [Chinese-DeepSeek-R1-Distill (zh)](https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT)
 - [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)
@@ -321,32 +394,32 @@ huggingface-cli login
 | 必需项       | 至少     | 推荐      |
 | ------------ | ------- | --------- |
-| python       | 3.8     | 3.11      |
+| python       | 3.9     | 3.10      |
-| torch        | 1.13.1  | 2.4.0     |
+| torch        | 1.13.1  | 2.5.1     |
-| transformers | 4.41.2  | 4.43.4    |
+| transformers | 4.41.2  | 4.49.0    |
-| datasets     | 2.16.0  | 2.20.0    |
+| datasets     | 2.16.0  | 3.2.0     |
-| accelerate   | 0.30.1  | 0.32.0    |
+| accelerate   | 0.34.0  | 1.2.1     |
 | peft         | 0.11.1  | 0.12.0    |
 | trl          | 0.8.6   | 0.9.6     |
 | 可选项       | 至少     | 推荐      |
 | ------------ | ------- | --------- |
 | CUDA         | 11.6    | 12.2      |
-| deepspeed    | 0.10.0  | 0.14.0    |
+| deepspeed    | 0.10.0  | 0.16.2    |
 | bitsandbytes | 0.39.0  | 0.43.1    |
-| vllm         | 0.4.3   | 0.5.0     |
+| vllm         | 0.4.3   | 0.7.3     |
-| flash-attn   | 2.3.0   | 2.6.3     |
+| flash-attn   | 2.3.0   | 2.7.2     |
 ### 硬件依赖
 \* *估算值*
 | 方法                      | 精度 |   7B  |  13B  |  30B  |   70B  |  110B  |  8x7B |  8x22B |
-| ----------------- | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
+| ------------------------ | ---- | ----- | ----- | ----- | ------ | ------ | ----- | ------ |
-| Full              | AMP  | 120GB | 240GB | 600GB | 1200GB | 2000GB | 900GB | 2400GB |
+| Full                     |  32  | 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 |
+| LoRA/GaLore/APOLLO/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 |
@@ -364,26 +437,47 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
-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
+可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、apollo、badam、adam-mini、qwen、minicpm_v、modelscope、openmind、swanlab、quality
 > [!TIP]
 > 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
+<details><summary>使用 <b>uv</b> 构建虚拟环境</summary>
+使用 [uv](https://github.com/astral-sh/uv) 创建隔离的 Python 环境：
+```bash
+uv sync --extra torch --extra metrics --prerelease=allow
+```
+在环境中运行 LLaMA-Factory：
+```bash
+uv run --prerelease=allow llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
+```
+</details>
 <details><summary>Windows 用户指南</summary>
+#### 安装 BitsAndBytes
 如果要在 Windows 平台上开启量化 LoRA（QLoRA），需要安装预编译的 `bitsandbytes` 库, 支持 CUDA 11.1 到 12.2, 请根据您的 CUDA 版本情况选择适合的[发布版本](https://github.com/jllllll/bitsandbytes-windows-webui/releases/tag/wheels)。
 ```bash
 pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.2.post2-py3-none-win_amd64.whl
 ```
-如果要在 Windows 平台上开启 FlashAttention-2，需要安装预编译的 `flash-attn` 库，支持 CUDA 12.1 到 12.2，请根据需求到 [flash-attention](https://github.com/bdashore3/flash-attention/releases) 下载对应版本安装。
+#### 安装 Flash Attention-2
+如果要在 Windows 平台上开启 FlashAttention-2，请使用 [flash-attention-windows-wheel](https://huggingface.co/lldacing/flash-attention-windows-wheel) 中的脚本自行编译与安装。
 </details>
 <details><summary>昇腾 NPU 用户指南</summary>
-在昇腾 NPU 设备上安装 LLaMA Factory 时，需要指定额外依赖项，使用 `pip install -e ".[torch-npu,metrics]"` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit 与 Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**，安装方法请参考[安装教程](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/80RC2alpha002/quickstart/quickstart/quickstart_18_0004.html)或使用以下命令：
+在昇腾 NPU 设备上安装 LLaMA Factory 时，请升级 Python 到 3.10 及以上，并需要指定额外依赖项，使用 `pip install -e ".[torch-npu,metrics]"` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit 与 Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**，安装方法请参考[安装教程](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/80RC2alpha002/quickstart/quickstart/quickstart_18_0004.html)或使用以下命令：
 ```bash
 # 请替换 URL 为 CANN 版本和设备型号对应的 URL
@@ -412,11 +506,45 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 下载预构建 Docker 镜像：[32GB](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html) | [64GB](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)
+#### 安装 BitsAndBytes
+如果要在 Ascend NPU 上进行基于 bitsandbytes 的 QLoRA 量化微调，请执行如下步骤：
+1. 手动编译 bitsandbytes：请参考[安装文档](https://huggingface.co/docs/bitsandbytes/installation?backend=Ascend+NPU&platform=Ascend+NPU)完成 NPU 版的 bitsandbytes 安装，编译要求环境 cmake 版本不低于 3.22.1，g++ 版本不低于 12.x。
+```bash
+# 从源码安装 bitsandbytes
+# 克隆 bitsandbytes 仓库, Ascend NPU 目前在 multi-backend-refactor 中支持
+git clone -b multi-backend-refactor https://github.com/bitsandbytes-foundation/bitsandbytes.git
+cd bitsandbytes/
+# 安装依赖
+pip install -r requirements-dev.txt
+# 安装编译工具依赖，该步骤在不同系统上命令有所不同，供参考
+apt-get install -y build-essential cmake
+# 编译 & 安装
+cmake -DCOMPUTE_BACKEND=npu -S .
+make
+pip install .
+```
+2. 安装 transformers 的 main 分支版本。
+```bash
+git clone -b main https://github.com/huggingface/transformers.git
+cd transformers
+pip install .
+```
+3. 在训练参数中设置 `double_quantization: false`，可参考[示例](examples/train_qlora/llama3_lora_sft_bnb_npu.yaml)。
 </details>
 ### 数据准备
-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。
+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 / Modelers 上的数据集或加载本地数据集。
 > [!NOTE]
 > 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
@@ -484,6 +612,7 @@ docker build -f ./docker/docker-cuda/Dockerfile \
 docker run -dit --gpus=all \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -p 7860:7860 \
@@ -508,6 +637,7 @@ docker build -f ./docker/docker-npu/Dockerfile \
 docker run -dit \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -v /usr/local/dcmi:/usr/local/dcmi \
@@ -541,6 +671,7 @@ docker build -f ./docker/docker-rocm/Dockerfile \
 docker run -dit \
    -v ./hf_cache:/root/.cache/huggingface \
    -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
    -v ./data:/app/data \
    -v ./output:/app/output \
    -v ./saves:/app/saves \
@@ -561,6 +692,7 @@ docker exec -it llamafactory bash
 - `hf_cache`：使用宿主机的 Hugging Face 缓存文件夹，允许更改为新的目录。
 - `ms_cache`：类似 Hugging Face 缓存文件夹，为 ModelScope 用户提供。
+- `om_cache`：类似 Hugging Face 缓存文件夹，为 Modelers 用户提供。
 - `data`：宿主机中存放数据集的文件夹路径。
 - `output`：将导出目录设置为该路径后，即可在宿主机中访问导出后的模型。
@@ -574,6 +706,8 @@ API_PORT=8000 llamafactory-cli api examples/inference/llama3_vllm.yaml
 > [!TIP]
 > API 文档请查阅[这里](https://platform.openai.com/docs/api-reference/chat/create)。
+>
+> 示例：[图像理解](scripts/api_example/test_image.py) | [工具调用](scripts/api_example/test_toolcall.py)
 ### 从魔搭社区下载
@@ -585,6 +719,16 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 将 `model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔搭社区](https://modelscope.cn/models)查看所有可用的模型，例如 `LLM-Research/Meta-Llama-3-8B-Instruct`。
+### 从魔乐社区下载
+您也可以通过下述方法，使用魔乐社区下载数据集和模型。
+```bash
+export USE_OPENMIND_HUB=1 # Windows 使用 `set USE_OPENMIND_HUB=1`
+```
+将 `model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔乐社区](https://modelers.cn/models)查看所有可用的模型，例如 `TeleAI/TeleChat-7B-pt`。
 ### 使用 W&B 面板
 若要使用 [Weights & Biases](https://wandb.ai) 记录实验数据，请在 yaml 文件中添加下面的参数。
@@ -596,6 +740,21 @@ run_name: test_run # 可选
 在启动训练任务时，将 `WANDB_API_KEY` 设置为[密钥](https://wandb.ai/authorize)来登录 W&B 账户。
+### 使用 SwanLab 面板
+若要使用 [SwanLab](https://github.com/SwanHubX/SwanLab) 记录实验数据，请在 yaml 文件中添加下面的参数。
+```yaml
+use_swanlab: true
+swanlab_run_name: test_run # 可选
+```
+在启动训练任务时，登录SwanLab账户有以下三种方式：
+方式一：在 yaml 文件中添加 `swanlab_api_key=<your_api_key>` ，并设置为你的 [API 密钥](https://swanlab.cn/settings)。
+方式二：将环境变量 `SWANLAB_API_KEY` 设置为你的 [API 密钥](https://swanlab.cn/settings)。
+方式三：启动前使用 `swanlab login` 命令完成登录。
 ## 使用了 LLaMA Factory 的项目
 如果您有项目希望添加至下述列表，请通过邮件联系或者创建一个 PR。
@@ -683,16 +842,20 @@ run_name: test_run # 可选
 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. Bai et al. Aligning Large Language Model with Direct Multi-Preference Optimization for Recommendation. CIKM 2024. [[paper]](https://dl.acm.org/doi/10.1145/3627673.3679611)
 1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: 天文大模型 StarWhisper，基于 ChatGLM2-6B 和 Qwen-14B 在天文数据上微调而得。
 1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: 中文法律领域大模型 DISC-LawLLM，基于 Baichuan-13B 微调而得，具有法律推理和知识检索能力。
 1. **[Sunsimiao](https://github.com/X-D-Lab/Sunsimiao)**: 孙思邈中文医疗大模型 Sumsimiao，基于 Baichuan-7B 和 ChatGLM-6B 在中文医疗数据上微调而得。
 1. **[CareGPT](https://github.com/WangRongsheng/CareGPT)**: 医疗大模型项目 CareGPT，基于 LLaMA2-7B 和 Baichuan-13B 在中文医疗数据上微调而得。
 1. **[MachineMindset](https://github.com/PKU-YuanGroup/Machine-Mindset/)**：MBTI性格大模型项目，根据数据集与训练方式让任意 LLM 拥有 16 个不同的性格类型。
-1. **[Luminia-13B-v3](https://huggingface.co/Nekochu/Luminia-13B-v3)**：一个用于生成 Stable Diffusion 提示词的大型语言模型。[[🤗Demo]](https://huggingface.co/spaces/Nekochu/Luminia-13B_SD_Prompt)
+1. **[Luminia-13B-v3](https://huggingface.co/Nekochu/Luminia-13B-v3)**：一个用于生成 Stable Diffusion 提示词的大型语言模型。[[demo]](https://huggingface.co/spaces/Nekochu/Luminia-13B_SD_Prompt)
 1. **[Chinese-LLaVA-Med](https://github.com/BUAADreamer/Chinese-LLaVA-Med)**：中文多模态医学大模型，基于 LLaVA-1.5-7B 在中文多模态医疗数据上微调而得。
 1. **[AutoRE](https://github.com/THUDM/AutoRE)**：基于大语言模型的文档级关系抽取系统。
 1. **[NVIDIA RTX AI Toolkit](https://github.com/NVIDIA/RTX-AI-Toolkit)**：在 Windows 主机上利用英伟达 RTX 设备进行大型语言模型微调的开发包。
 1. **[LazyLLM](https://github.com/LazyAGI/LazyLLM)**：一个低代码构建多 Agent 大模型应用的开发工具，支持基于 LLaMA Factory 的模型微调.
+1. **[RAG-Retrieval](https://github.com/NLPJCL/RAG-Retrieval)**：一个全链路 RAG 检索模型微调、推理和蒸馏代码库。[[blog]](https://zhuanlan.zhihu.com/p/987727357)
+1. **[360-LLaMA-Factory](https://github.com/Qihoo360/360-LLaMA-Factory)**：一个魔改后的代码库，通过 Ring Attention 支持长序列的 SFT 和 DPO 训练。
+1. **[Sky-T1](https://novasky-ai.github.io/posts/sky-t1/)**：由 NovaSky AI 微调的低成本类 o1 长推理模型。
 </details>
@@ -700,7 +863,7 @@ run_name: test_run # 可选
 本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。
-使用模型权重时，请遵循对应的模型协议：[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)
+使用模型权重时，请遵循对应的模型协议：[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) / [GPT-2](https://github.com/openai/gpt-2/blob/master/LICENSE) / [Granite](LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM](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/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3/Phi-4](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [Skywork](https://huggingface.co/Skywork/Skywork-13B-base/blob/main/Skywork%20Community%20License.pdf) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [TeleChat2](https://huggingface.co/Tele-AI/telechat-7B/blob/main/TeleChat%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf) / [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)
 ## 引用

--- 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
@@ -24,6 +24,7 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
    "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)",
+    "audios": "the column name in the dataset containing the audios 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)"
@@ -150,6 +151,10 @@ An additional column `images` is required. Please refer to the [sharegpt](#share
 An additional column `videos` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
+### Multimodal Audio Dataset
+An additional column `audios` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
 ## Sharegpt Format
 ### Supervised Fine-Tuning Dataset
@@ -296,7 +301,7 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 - [Example dataset](mllm_demo.json)
-Multimodal image datasets require a `images` column containing the paths to the input images.
+Multimodal image datasets require an `images` column containing the paths to the input images.
 The number of images should be identical to the `<image>` tokens in the conversations.
@@ -374,6 +379,47 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 }
 ```
+### Multimodal Audio Dataset
+- [Example dataset](mllm_audio_demo.json)
+Multimodal audio datasets require an `audios` column containing the paths to the input audios.
+The number of audios should be identical to the `<audio>` tokens in the conversations.
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<audio>human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "audios": [
+      "audio 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",
+    "audios": "audios"
+  }
+}
+```
 ### OpenAI Format
 The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.

--- a/data/README_zh.md
+++ b/data/README_zh.md
@@ -24,6 +24,7 @@
    "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）",
+    "audios": "数据集代表音频输入的表头名称（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）"
@@ -150,6 +151,10 @@ KTO 数据集需要提供额外的 `kto_tag` 列。详情请参阅 [sharegpt](#s
 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)。
+### 多模态音频数据集
+多模态音频数据集需要提供额外的 `audios` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
 ## Sharegpt 格式
 ### 指令监督微调数据集
@@ -374,6 +379,48 @@ KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人
 }
 ```
+### 多模态音频数据集
+- [样例数据集](mllm_audio_demo.json)
+多模态音频数据集需要额外添加一个 `audios` 列，包含输入音频的路径。
+注意音频的数量必须与文本中所有 `<audio>` 标记的数量严格一致。
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<audio>人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "audios": [
+      "音频路径（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",
+    "audios": "audios"
+  }
+}
+```
 ### 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。

--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -38,6 +38,20 @@
      "assistant_tag": "assistant"
    }
  },
+  "mllm_audio_demo": {
+    "file_name": "mllm_audio_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "audios": "audios"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
  "mllm_video_demo": {
    "file_name": "mllm_video_demo.json",
    "formatting": "sharegpt",
@@ -304,6 +318,38 @@
      "response": "response"
    }
  },
+  "open_thoughts": {
+    "hf_hub_url": "llamafactory/OpenThoughts-114k",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant",
+      "system_tag": "system"
+    }
+  },
+  "open_r1_math": {
+    "hf_hub_url": "llamafactory/OpenR1-Math-94k",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant",
+      "system_tag": "system"
+    }
+  },
+  "chinese_r1_distill": {
+    "hf_hub_url": "Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT",
+    "ms_hub_url": "liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT"
+  },
  "llava_1k_en": {
    "hf_hub_url": "BUAADreamer/llava-en-zh-2k",
    "subset": "en",

--- a/data/mllm_audio_demo.json
+++ b/data/mllm_audio_demo.json
+[
+  {
+    "messages": [
+      {
+        "content": "<audio>What's that sound?",
+        "role": "user"
+      },
+      {
+        "content": "It is the sound of glass shattering.",
+        "role": "assistant"
+      }
+    ],
+    "audios": [
+      "mllm_demo_data/1.mp3"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "<audio>What can you hear?",
+        "role": "user"
+      },
+      {
+        "content": "A woman is coughing.",
+        "role": "assistant"
+      }
+    ],
+    "audios": [
+      "mllm_demo_data/2.wav"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "<audio>What does the person say?",
+        "role": "user"
+      },
+      {
+        "content": "Mister Quiller is the apostle of the middle classes and we are glad to welcome his gospel.",
+        "role": "assistant"
+      }
+    ],
+    "audios": [
+      "mllm_demo_data/3.flac"
+    ]
+  }
+]
--- a/data/mllm_demo_data/1.mp3
+++ b/data/mllm_demo_data/1.mp3
--- a/data/mllm_demo_data/2.wav
+++ b/data/mllm_demo_data/2.wav
--- a/data/mllm_demo_data/3.flac
+++ b/data/mllm_demo_data/3.flac
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
-FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.2-py3.10
--- a/docker/docker-cuda/Dockerfile
+++ b/docker/docker-cuda/Dockerfile
@@ -17,16 +17,28 @@ ARG INSTALL_LIGER_KERNEL=false
 ARG INSTALL_HQQ=false
 ARG INSTALL_EETQ=false
 ARG PIP_INDEX=https://pypi.org/simple
+ARG HTTP_PROXY=
 # Set the working directory
 WORKDIR /app
+# Set http proxy
+RUN if [ -n "$HTTP_PROXY" ]; then \
+        echo "Configuring proxy..."; \
+        export http_proxy=$HTTP_PROXY; \
+        export https_proxy=$HTTP_PROXY; \
+    fi
 # Install the requirements
 COPY requirements.txt /app
 RUN pip config set global.index-url "$PIP_INDEX" && \
    pip config set global.extra-index-url "$PIP_INDEX" && \
    python -m pip install --upgrade pip && \
-    python -m pip install -r requirements.txt
+    if [ -n "$HTTP_PROXY" ]; then \
+        python -m pip install --proxy=$HTTP_PROXY -r requirements.txt; \
+    else \
+        python -m pip install -r requirements.txt; \
+    fi
 # Copy the rest of the application into the image
 COPY . /app
@@ -51,13 +63,30 @@ RUN EXTRA_PACKAGES="metrics"; \
    if [ "$INSTALL_EETQ" == "true" ]; then \
        EXTRA_PACKAGES="${EXTRA_PACKAGES},eetq"; \
    fi; \
-    pip install -e ".[$EXTRA_PACKAGES]"
+    if [ -n "$HTTP_PROXY" ]; then \
+        pip install --proxy=$HTTP_PROXY -e ".[$EXTRA_PACKAGES]"; \
+    else \
+        pip install -e ".[$EXTRA_PACKAGES]"; \
+    fi
 # Rebuild flash attention
 RUN pip uninstall -y transformer-engine flash-attn && \
    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
-        pip uninstall -y ninja && pip install ninja && \
+        pip uninstall -y ninja && \
+        if [ -n "$HTTP_PROXY" ]; then \
+            pip install --proxy=$HTTP_PROXY ninja && \
+            pip install --proxy=$HTTP_PROXY --no-cache-dir flash-attn --no-build-isolation; \
+        else \
+            pip install ninja && \
            pip install --no-cache-dir flash-attn --no-build-isolation; \
+        fi; \
+    fi
+# Unset http proxy
+RUN if [ -n "$HTTP_PROXY" ]; then \
+        unset http_proxy; \
+        unset https_proxy; \
    fi
 # Set up volumes

--- 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:8.0.0-910b-ubuntu22.04-py3.10
 # FROM ascendai/cann:8.0.rc1-910-openeuler22.03-py3.8
 # FROM ascendai/cann:8.0.rc1-910b-openeuler22.03-py3.8
@@ -12,16 +12,28 @@ ENV DEBIAN_FRONTEND=noninteractive
 ARG INSTALL_DEEPSPEED=false
 ARG PIP_INDEX=https://pypi.org/simple
 ARG TORCH_INDEX=https://download.pytorch.org/whl/cpu
+ARG HTTP_PROXY=
 # Set the working directory
 WORKDIR /app
+# Set http proxy
+RUN if [ -n "$HTTP_PROXY" ]; then \
+        echo "Configuring proxy..."; \
+        export http_proxy=$HTTP_PROXY; \
+        export https_proxy=$HTTP_PROXY; \
+    fi
 # Install the requirements
 COPY requirements.txt /app
 RUN pip config set global.index-url "$PIP_INDEX" && \
    pip config set global.extra-index-url "$TORCH_INDEX" && \
    python -m pip install --upgrade pip && \
-    python -m pip install -r requirements.txt
+    if [ -n "$HTTP_PROXY" ]; then \
+        python -m pip install --proxy=$HTTP_PROXY -r requirements.txt; \
+    else \
+        python -m pip install -r requirements.txt; \
+    fi
 # Copy the rest of the application into the image
 COPY . /app
@@ -31,7 +43,17 @@ RUN EXTRA_PACKAGES="torch-npu,metrics"; \
    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
    fi; \
-    pip install -e ".[$EXTRA_PACKAGES]"
+    if [ -n "$HTTP_PROXY" ]; then \
+        pip install --proxy=$HTTP_PROXY -e ".[$EXTRA_PACKAGES]"; \
+    else \
+        pip install -e ".[$EXTRA_PACKAGES]"; \
+    fi
+# Unset http proxy
+RUN if [ -n "$HTTP_PROXY" ]; then \
+        unset http_proxy; \
+        unset https_proxy; \
+    fi
 # Set up volumes
 VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]

--- a/docker/docker-npu/docker-compose.yml
+++ b/docker/docker-npu/docker-compose.yml
@@ -4,7 +4,7 @@ services:
      dockerfile: ./docker/docker-npu/Dockerfile
      context: ../..
      args:
-        INSTALL_DEEPSPEED: false
+        INSTALL_DEEPSPEED: "false"
        PIP_INDEX: https://pypi.org/simple
    container_name: llamafactory
    volumes:

--- a/docker/docker-rocm/Dockerfile
+++ b/docker/docker-rocm/Dockerfile
@@ -13,16 +13,28 @@ ARG INSTALL_FLASHATTN=false
 ARG INSTALL_LIGER_KERNEL=false
 ARG INSTALL_HQQ=false
 ARG PIP_INDEX=https://pypi.org/simple
+ARG HTTP_PROXY=
 # Set the working directory
 WORKDIR /app
+# Set http proxy
+RUN if [ -n "$HTTP_PROXY" ]; then \
+        echo "Configuring proxy..."; \
+        export http_proxy=$HTTP_PROXY; \
+        export https_proxy=$HTTP_PROXY; \
+    fi
 # Install the requirements
 COPY requirements.txt /app
 RUN pip config set global.index-url "$PIP_INDEX" && \
    pip config set global.extra-index-url "$PIP_INDEX" && \
    python -m pip install --upgrade pip && \
-    python -m pip install -r requirements.txt
+    if [ -n "$HTTP_PROXY" ]; then \
+        python -m pip install --proxy=$HTTP_PROXY -r requirements.txt; \
+    else \
+        python -m pip install -r requirements.txt; \
+    fi
 # Copy the rest of the application into the image
 COPY . /app
@@ -44,13 +56,29 @@ RUN EXTRA_PACKAGES="metrics"; \
    if [ "$INSTALL_HQQ" == "true" ]; then \
        EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
    fi; \
-    pip install -e ".[$EXTRA_PACKAGES]"
+    if [ -n "$HTTP_PROXY" ]; then \
+        pip install --proxy=$HTTP_PROXY -e ".[$EXTRA_PACKAGES]"; \
+    else \
+        pip install -e ".[$EXTRA_PACKAGES]"; \
+    fi
 # Rebuild flash attention
 RUN pip uninstall -y transformer-engine flash-attn && \
    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
-        pip uninstall -y ninja && pip install ninja && \
+        pip uninstall -y ninja && \
+        if [ -n "$HTTP_PROXY" ]; then \
+            pip install --proxy=$HTTP_PROXY ninja && \
+            pip install --proxy=$HTTP_PROXY --no-cache-dir flash-attn --no-build-isolation; \
+        else \
+            pip install ninja && \
            pip install --no-cache-dir flash-attn --no-build-isolation; \
+        fi; \
+    fi
+# Unset http proxy
+RUN if [ -n "$HTTP_PROXY" ]; then \
+        unset http_proxy; \
+        unset https_proxy; \
    fi
 # Set up volumes

--- a/examples/README.md
+++ b/examples/README.md
@@ -98,7 +98,7 @@ FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ds3.
 #### Supervised Fine-Tuning with Ray on 4 GPUs
 ```bash
-USE_RAY=1 llamafactory-cli train examples/train_full/llama3_lora_sft_ray.yaml
+USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
 ```
 ### QLoRA Fine-Tuning
@@ -170,6 +170,12 @@ llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
 llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
 ```
+### Save Ollama modelfile
+```bash
+llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
+```
 ### Inferring LoRA Fine-Tuned Models
 #### Batch Generation using vLLM Tensor Parallel