Add files using upload-large-folder tool

.ipynb_checkpoints/llm_downloader-checkpoint.py

@@ -0,0 +1,13 @@
+from huggingface_hub import snapshot_download
+repo_id = "Qwen/QwQ-32B"
+md = "/workspace/Qwen/QwQ-32B"
+
+snapshot_download(
+    repo_id=repo_id,
+    cache_dir=md,
+    local_dir=md,
+    # repo_type="dataset",
+    local_dir_use_symlinks=False,
+    # resume_download=True,
+    ignore_patterns=["original/*"],
+)

LlamaFactory/.dockerignore

@@ -0,0 +1,15 @@
+.vscode
+.git
+.github
+.venv
+cache
+docker
+saves
+hf_cache
+ms_cache
+om_cache
+shared_data
+output
+.dockerignore
+.gitattributes
+.gitignore

LlamaFactory/.env.local

@@ -0,0 +1,45 @@
+# Note: actually we do not support .env, just for reference
+# api
+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=
+USE_RAY=
+USE_KT=
+RECORD_VRAM=
+OPTIM_TORCH=
+NPU_JIT_COMPILE=
+# torchrun
+FORCE_TORCHRUN=
+MASTER_ADDR=
+MASTER_PORT=
+NNODES=
+NODE_RANK=
+NPROC_PER_NODE=
+# wandb
+WANDB_DISABLED=
+WANDB_PROJECT=
+WANDB_API_KEY=
+# gradio ui
+GRADIO_SHARE=
+GRADIO_SERVER_NAME=
+GRADIO_SERVER_PORT=
+GRADIO_ROOT_PATH=
+GRADIO_IPV6=
+# backend
+USE_MCA=
+# setup
+ENABLE_SHORT_CONSOLE=
+# reserved (do not use)
+LLAMABOARD_ENABLED=
+LLAMABOARD_WORKDIR=

LlamaFactory/.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

LlamaFactory/.gitignore

@@ -0,0 +1,183 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# vscode
+.vscode/
+
+# uv
+uv.lock
+
+# macOS
+.DS_Store
+
+# custom .gitignore
+hf_cache/
+ms_cache/
+om_cache/
+llamaboard_cache/
+llamaboard_config/
+saves/
+output/
+outputs/
+wandb/
+swanlog/
+generated_predictions.jsonl
+predictions_score.json

LlamaFactory/.pre-commit-config.yaml

@@ -0,0 +1,28 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+    -   id: check-ast
+    -   id: check-added-large-files
+        args: ['--maxkb=25000']
+    -   id: check-merge-conflict
+    -   id: check-yaml
+    -   id: debug-statements
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
+    -   id: no-commit-to-branch
+        args: ['--branch', 'main']
+
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v3.20.0
+    hooks:
+    -   id: pyupgrade
+        args: [--py39-plus]
+
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.13.2
+    hooks:
+    -   id: ruff
+        args: [--fix]
+    -   id: ruff-format

LlamaFactory/CITATION.cff

@@ -0,0 +1,44 @@
+cff-version: 1.2.0
+date-released: 2024-03
+message: "If you use this software, please cite it as below."
+authors:
+- family-names: "Zheng"
+  given-names: "Yaowei"
+- family-names: "Zhang"
+  given-names: "Richong"
+- family-names: "Zhang"
+  given-names: "Junhao"
+- family-names: "Ye"
+  given-names: "Yanhan"
+- family-names: "Luo"
+  given-names: "Zheyan"
+- family-names: "Feng"
+  given-names: "Zhangchi"
+- family-names: "Ma"
+  given-names: "Yongqiang"
+title: "LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models"
+url: "https://arxiv.org/abs/2403.13372"
+preferred-citation:
+  type: conference-paper
+  conference:
+    name: "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
+  authors:
+    - family-names: "Zheng"
+      given-names: "Yaowei"
+    - family-names: "Zhang"
+      given-names: "Richong"
+    - family-names: "Zhang"
+      given-names: "Junhao"
+    - family-names: "Ye"
+      given-names: "Yanhan"
+    - family-names: "Luo"
+      given-names: "Zheyan"
+    - family-names: "Feng"
+      given-names: "Zhangchi"
+    - family-names: "Ma"
+      given-names: "Yongqiang"
+  title: "LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models"
+  url: "https://arxiv.org/abs/2403.13372"
+  year: 2024
+  publisher: "Association for Computational Linguistics"
+  address: "Bangkok, Thailand"

LlamaFactory/LICENSE

@@ -0,0 +1,201 @@
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

LlamaFactory/MANIFEST.in

@@ -0,0 +1 @@
+include LICENSE

LlamaFactory/Makefile

@@ -0,0 +1,28 @@
+.PHONY: build commit license quality style test
+
+check_dirs := scripts src tests tests_v1
+
+RUN := $(shell command -v uv >/dev/null 2>&1 && echo "uv run" || echo "")
+BUILD := $(shell command -v uv >/dev/null 2>&1 && echo "uv build" || echo "python -m build")
+TOOL := $(shell command -v uv >/dev/null 2>&1 && echo "uvx" || echo "")
+
+build:
+	$(BUILD)
+
+commit:
+	$(TOOL) pre-commit install
+	$(TOOL) pre-commit run --all-files
+
+license:
+	$(RUN) python3 tests/check_license.py $(check_dirs)
+
+quality:
+	$(TOOL) ruff check $(check_dirs)
+	$(TOOL) ruff format --check $(check_dirs)
+
+style:
+	$(TOOL) ruff check $(check_dirs) --fix
+	$(TOOL) ruff format $(check_dirs)
+
+test:
+	WANDB_DISABLED=true $(RUN) pytest -vv --import-mode=importlib tests/ tests_v1/

LlamaFactory/README.md

@@ -0,0 +1,957 @@
+![# 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 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-1000+-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
+[![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags)
+
+[![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
+[![Discord](assets/thirdparty/discord.svg)](https://discord.gg/rKfvV9r9FK)
+[![WeChat](https://img.shields.io/badge/WeChat-User%20Group-blue?logo=wechat)](https://github.com/hiyouga/llamafactory-community)
+[![Blog](https://img.shields.io/badge/Hugo-Official%20Blog-blue?logo=hugo)](https://blog.llamafactory.net/en/)
+
+[![Open in Colab](assets/thirdparty/colab.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing)
+[![Open in DSW](assets/thirdparty/dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)
+[![Open in Lab4ai](assets/thirdparty/lab4ai.svg)](https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46&utm_source=LLaMA-Factory)
+[![Open in Online](assets/thirdparty/online.svg)](https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory)
+[![Open in Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
+[![Open in Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)
+[![Open in Novita](https://img.shields.io/badge/Novita-Deploy%20Template-blue)](https://novita.ai/templates-library/105981?sharer=88115474-394e-4bda-968e-b88e123d0c47)
+
+### Used by [Amazon](https://aws.amazon.com/cn/blogs/machine-learning/how-apoidea-group-enhances-visual-information-extraction-from-banking-documents-with-multimodal-models-using-llama-factory-on-amazon-sagemaker-hyperpod/), [NVIDIA](https://developer.nvidia.com/rtx/ai-toolkit), [Aliyun](https://help.aliyun.com/zh/pai/use-cases/fine-tune-a-llama-3-model-with-llama-factory), etc.
+
+<div align="center" markdown="1">
+
+### Supporters ❤️
+
+| <div style="text-align: center;"><a href="https://warp.dev/llama-factory"><img alt="Warp sponsorship" width="400" src="assets/sponsors/warp.jpg"></a><br><a href="https://warp.dev/llama-factory" style="font-size:larger;">Warp, the agentic terminal for developers</a><br><a href="https://warp.dev/llama-factory">Available for MacOS, Linux, & Windows</a> | <a href="https://serpapi.com"><img alt="SerpAPI sponsorship" width="250" src="assets/sponsors/serpapi.svg"> </a> |
+| ---- | ---- |
+
+----
+
+### Easily fine-tune 100+ large language models with zero-code [CLI](#quickstart) and [Web UI](#fine-tuning-with-llama-board-gui-powered-by-gradio)
+
+![GitHub Trend](https://trendshift.io/api/badge/repositories/4535)
+
+</div>
+
+👋 Join our [WeChat](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/main.jpg), [NPU](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/npu.jpg), [Lab4AI](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/lab4ai.jpg), [LLaMA Factory Online](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/online.jpg) user group.
+
+\[ English | [中文](README_zh.md) \]
+
+**Fine-tuning a large language model can be easy as...**
+
+https://github.com/user-attachments/assets/3991a3a8-4276-4d30-9cab-4cb0c4b9b99e
+
+Start local training:
+- Please refer to [usage](#getting-started)
+
+Start cloud training:
+- **Colab (free)**: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing
+- **PAI-DSW (free trial)**: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
+- **LLaMA Factory Online**: https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory
+- **Alaya NeW (cloud GPU deal)**: https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory
+
+Read technical notes:
+- **Documentation (WIP)**: https://llamafactory.readthedocs.io/en/latest/
+- **Documentation (AMD GPU)**: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/notebooks/fine_tune/llama_factory_llama3.html
+- **Official Blog**: https://blog.llamafactory.net/en/
+- **Official Course**: https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46&utm_source=LLaMA-Factory
+
+> [!NOTE]
+> Except for the above links, all other websites are unauthorized third-party websites. Please carefully use them.
+
+## Table of Contents
+
+- [Features](#features)
+- [Blogs](#blogs)
+- [Changelog](#changelog)
+- [Supported Models](#supported-models)
+- [Supported Training Approaches](#supported-training-approaches)
+- [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)
+  - [LLaMA Factory Online](#llama-factory-online)
+  - [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)
+- [Acknowledgement](#acknowledgement)
+
+## Features
+
+- **Various models**: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen3, Qwen3-VL, DeepSeek, Gemma, GLM, 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), [APOLLO](https://github.com/zhuhanqing/APOLLO), [Adam-mini](https://github.com/zyushun/Adam-mini), [Muon](https://github.com/KellerJordan/Muon), [OFT](https://github.com/huggingface/peft/tree/main/src/peft/tuners/oft), 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), [KTransformers](https://github.com/kvcache-ai/ktransformers/), RoPE scaling, NEFTune and rsLoRA.
+- **Wide tasks**: Multi-turn dialogue, tool using, image understanding, visual grounding, video recognition, audio understanding, etc.
+- **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, [SwanLab](https://github.com/SwanHubX/SwanLab), etc.
+- **Faster inference**: OpenAI-style API, Gradio UI and CLI with [vLLM worker](https://github.com/vllm-project/vllm) or [SGLang worker](https://github.com/sgl-project/sglang).
+
+### Day-N Support for Fine-Tuning Cutting-Edge Models
+
+| Support Date | Model Name                                                           |
+| ------------ | -------------------------------------------------------------------- |
+| Day 0        | Qwen3 / Qwen2.5-VL / Gemma 3 / GLM-4.1V / InternLM 3 / MiniCPM-o-2.6 |
+| Day 1        | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4               |
+
+## Blogs
+
+> [!TIP]
+> Now we have a dedicated blog for LLaMA Factory!
+>
+> Website: https://blog.llamafactory.net/en/
+
+- 💡 [KTransformers Fine-Tuning × LLaMA Factory: Fine-tuning 1000 Billion models with 2 4090-GPU + CPU](https://blog.llamafactory.net/en/posts/ktransformers/) (English)
+- 💡 [Easy Dataset × LLaMA Factory: Enabling LLMs to Efficiently Learn Domain Knowledge](https://buaa-act.feishu.cn/wiki/GVzlwYcRFiR8OLkHbL6cQpYin7g) (English)
+- [Fine-tune a mental health LLM using LLaMA-Factory](https://www.lab4ai.cn/project/detail?id=25cce32ec131497b9e06a93336a0817f&type=project&utm_source=LLaMA-Factory) (Chinese)
+- [Fine-tune GPT-OSS for Role-Playing using LLaMA-Factory](https://docs.llamafactory.com.cn/docs/documents/best-practice/gptroleplay/?utm_source=LLaMA-Factory) (Chinese)
+- [A One-Stop Code-Free Model Reinforcement Learning and Deployment Platform based on LLaMA-Factory and EasyR1](https://aws.amazon.com/cn/blogs/china/building-llm-model-hub-based-on-llamafactory-and-easyr1/) (Chinese)
+- [How Apoidea Group enhances visual information extraction from banking documents with multimodal models using LLaMA-Factory on Amazon SageMaker HyperPod](https://aws.amazon.com/cn/blogs/machine-learning/how-apoidea-group-enhances-visual-information-extraction-from-banking-documents-with-multimodal-models-using-llama-factory-on-amazon-sagemaker-hyperpod/) (English)
+
+<details><summary>All Blogs</summary>
+
+- [Fine-tune Llama3.1-70B for Medical Diagnosis using LLaMA-Factory](https://docs.alayanew.com/docs/documents/bestPractice/bigModel/llama70B/?utm_source=LLaMA-Factory) (Chinese)
+- [Fine-tune Qwen2.5-VL for Autonomous Driving using LLaMA-Factory](https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory) (Chinese)
+- [LLaMA Factory: Fine-tuning the DeepSeek-R1-Distill-Qwen-7B Model for News Classifier](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b) (Chinese)
+- [A One-Stop Code-Free Model Fine-Tuning \& Deployment Platform based on SageMaker and LLaMA-Factory](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/) (Chinese)
+- [LLaMA Factory Multi-Modal Fine-Tuning Practice: Fine-Tuning Qwen2-VL for Personal Tourist Guide](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl) (Chinese)
+- [LLaMA Factory: Fine-tuning Llama3 for Role-Playing](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) (Chinese)
+
+</details>
+
+## Changelog
+
+[25/10/26] We support Megatron-core training backend with [**mcore_adapter**](https://github.com/alibaba/ROLL/tree/main/mcore_adapter). See [PR #9237](https://github.com/hiyouga/LLaMA-Factory/pull/9237) to get started.
+
+[25/08/22] We supported **[OFT](https://arxiv.org/abs/2306.07280)** and **[OFTv2](https://arxiv.org/abs/2506.19847)**. See [examples](examples/README.md) for usage.
+
+[25/08/20] We supported fine-tuning the **[Intern-S1-mini](https://huggingface.co/internlm/Intern-S1-mini)** models. See [PR #8976](https://github.com/hiyouga/LLaMA-Factory/pull/8976) to get started.
+
+[25/08/06] We supported fine-tuning the **[GPT-OSS](https://github.com/openai/gpt-oss)** models. See [PR #8826](https://github.com/hiyouga/LLaMA-Factory/pull/8826) to get started.
+
+<details><summary>Full Changelog</summary>
+
+[25/07/02] We supported fine-tuning the **[GLM-4.1V-9B-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)** model.
+
+[25/04/28] We supported fine-tuning the **[Qwen3](https://qwenlm.github.io/blog/qwen3/)** model family.
+
+[25/04/21] We supported the **[Muon](https://github.com/KellerJordan/Muon)** optimizer. See [examples](examples/README.md) for usage. Thank [@tianshijing](https://github.com/tianshijing)'s PR.
+
+[25/04/16] We supported fine-tuning the **[InternVL3](https://huggingface.co/OpenGVLab/InternVL3-8B)** model. See [PR #7258](https://github.com/hiyouga/LLaMA-Factory/pull/7258) to get started.
+
+[25/04/14] We supported fine-tuning the **[GLM-Z1](https://huggingface.co/THUDM/GLM-Z1-9B-0414)** and **[Kimi-VL](https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct)** models.
+
+[25/04/06] We supported fine-tuning the **[Llama 4](https://ai.meta.com/blog/llama-4-multimodal-intelligence/)** model. See [PR #7611](https://github.com/hiyouga/LLaMA-Factory/pull/7611) to get started.
+
+[25/03/31] We supported fine-tuning the **[Qwen2.5 Omni](https://qwenlm.github.io/blog/qwen2.5-omni/)** model. See [PR #7537](https://github.com/hiyouga/LLaMA-Factory/pull/7537) to get started.
+
+[25/03/15] We supported **[SGLang](https://github.com/sgl-project/sglang)** as inference backend. Try `infer_backend: sglang` to accelerate inference.
+
+[25/03/12] We supported fine-tuning the **[Gemma 3](https://huggingface.co/blog/gemma3)** model.
+
+[25/02/24] Announcing **[EasyR1](https://github.com/hiyouga/EasyR1)**, an efficient, scalable and multi-modality RL training framework for efficient GRPO training.
+
+[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.
+
+[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.
+
+[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)** models.
+
+[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 **[InternLM 3](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.
+
+[24/08/27] 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.
+
+[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)**. 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>
+
+> [!TIP]
+> If you cannot use the latest feature, please pull the latest code and install LLaMA-Factory again.
+
+## Supported Models
+
+| Model                                                             | Model size                       | Template             |
+| ----------------------------------------------------------------- | -------------------------------- | -------------------- |
+| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                    |
+| [DeepSeek (LLM/Code/MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | deepseek             |
+| [DeepSeek 3-3.2](https://huggingface.co/deepseek-ai)              | 236B/671B                        | deepseek3            |
+| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai)       | 1.5B/7B/8B/14B/32B/70B/671B      | deepseekr1           |
+| [ERNIE-4.5](https://huggingface.co/baidu)                         | 0.3B/21B/300B                    | ernie_nothink        |
+| [Falcon/Falcon H1](https://huggingface.co/tiiuae)                 | 0.5B/1.5B/3B/7B/11B/34B/40B/180B | falcon/falcon_h1     |
+| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma/gemma2         |
+| [Gemma 3/Gemma 3n](https://huggingface.co/google)                 | 270M/1B/4B/6B/8B/12B/27B         | gemma3/gemma3n       |
+| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/zai-org)         | 9B/32B                           | glm4/glmz1           |
+| [GLM-4.5/GLM-4.5(6)V](https://huggingface.co/zai-org)             | 9B/106B/355B                     | glm4_moe/glm4_5v     |
+| [GPT-2](https://huggingface.co/openai-community)                  | 0.1B/0.4B/0.8B/1.5B              | -                    |
+| [GPT-OSS](https://huggingface.co/openai)                          | 20B/120B                         | gpt_oss              |
+| [Granite 3-4](https://huggingface.co/ibm-granite)                 | 1B/2B/3B/7B/8B                   | granite3/granite4    |
+| [Hunyuan/Hunyuan1.5 (MT)](https://huggingface.co/tencent/)        | 0.5B/1.8B/4B/7B/13B              | hunyuan/hunyuan_small |
+| [InternLM 2-3](https://huggingface.co/internlm)                   | 7B/8B/20B                        | intern2              |
+| [InternVL 2.5-3.5](https://huggingface.co/OpenGVLab)              | 1B/2B/4B/8B/14B/30B/38B/78B/241B | intern_vl            |
+| [Intern-S1-mini](https://huggingface.co/internlm/)                | 8B                               | intern_s1            |
+| [Kimi-VL](https://huggingface.co/moonshotai)                      | 16B                              | kimi_vl              |
+| [Ling 2.0 (mini/flash)](https://huggingface.co/inclusionAI)       | 16B/100B                         | bailing_v2           |
+| [LFM 2.5 (VL)](https://huggingface.co/LiquidAI)                   | 1.2B/1.6B                        | lfm2/lfm2_vl         |
+| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -                    |
+| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2               |
+| [Llama 3-3.3](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3               |
+| [Llama 4](https://huggingface.co/meta-llama)                      | 109B/402B                        | llama4               |
+| [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     |
+| [MiMo](https://huggingface.co/XiaomiMiMo)                         | 7B/309B                          | mimo/mimo_v2         |
+| [MiniCPM 4](https://huggingface.co/openbmb)                       | 0.5B/8B                          | cpm4                 |
+| [MiniCPM-o-2.6/MiniCPM-V-2.6](https://huggingface.co/openbmb)     | 8B                               | minicpm_o/minicpm_v  |
+| [MiniMax-M1/MiniMax-M2](https://huggingface.co/MiniMaxAI/models)  | 229B/456B                        | minimax1/minimax2    |
+| [Ministral 3](https://huggingface.co/mistralai)                   | 3B/8B/14B                        | ministral3           |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral              |
+| [PaliGemma/PaliGemma2](https://huggingface.co/google)             | 3B/10B/28B                       | paligemma            |
+| [Phi-3/Phi-3.5](https://huggingface.co/microsoft)                 | 4B/14B                           | phi                  |
+| [Phi-3-small](https://huggingface.co/microsoft)                   | 7B                               | phi_small            |
+| [Phi-4-mini/Phi-4](https://huggingface.co/microsoft)              | 3.8B/14B                         | phi4_mini/phi4       |
+| [Pixtral](https://huggingface.co/mistralai)                       | 12B                              | pixtral              |
+| [Qwen2 (Code/Math/MoE/QwQ)](https://huggingface.co/Qwen)          | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen                 |
+| [Qwen3 (MoE/Instruct/Thinking/Next)](https://huggingface.co/Qwen) | 0.6B/1.7B/4B/8B/14B/32B/80B/235B | qwen3/qwen3_nothink  |
+| [Qwen2-Audio](https://huggingface.co/Qwen)                        | 7B                               | qwen2_audio          |
+| [Qwen2.5-Omni](https://huggingface.co/Qwen)                       | 3B/7B                            | qwen2_omni           |
+| [Qwen3-Omni](https://huggingface.co/Qwen)                         | 30B                              | qwen3_omni           |
+| [Qwen2-VL/Qwen2.5-VL/QVQ](https://huggingface.co/Qwen)            | 2B/3B/7B/32B/72B                 | qwen2_vl             |
+| [Qwen3-VL](https://huggingface.co/Qwen)                           | 2B/4B/8B/30B/32B/235B            | qwen3_vl             |
+| [Seed (OSS/Coder)](https://huggingface.co/ByteDance-Seed)         | 8B/36B                           | seed_oss/seed_coder  |
+| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                    |
+| [TeleChat 2-2.5](https://huggingface.co/Tele-AI)                  | 3B/7B/35B/115B                   | telechat2            |
+| [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.
+>
+> If the model has both reasoning and non-reasoning versions, please use the `_nothink` suffix to distinguish between them. For example, `qwen3` and `qwen3_nothink`.
+>
+> Remember to use the **SAME** template in training and inference.
+>
+> \*: You should install the `transformers` from main branch and use `DISABLE_VERSION_CHECK=1` to skip version check.
+>
+> \*\*: You need to install a specific version of `transformers` to use the corresponding model.
+
+Please refer to [constants.py](src/llamafactory/extras/constants.py) for a full list of models we supported.
+
+You also can add a custom chat template to [template.py](src/llamafactory/data/template.py).
+
+## Supported Training Approaches
+
+| Approach               |     Full-tuning    |    Freeze-tuning   |       LoRA         |       QLoRA        |        OFT         |        QOFT        |
+| ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ | ------------------ | ------------------ |
+| Pre-Training           | :white_check_mark: | :white_check_mark: | :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: | :white_check_mark: | :white_check_mark: |
+| Reward Modeling        | :white_check_mark: | :white_check_mark: | :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: | :white_check_mark: | :white_check_mark: |
+| DPO Training           | :white_check_mark: | :white_check_mark: | :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: | :white_check_mark: | :white_check_mark: |
+| ORPO Training          | :white_check_mark: | :white_check_mark: | :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: | :white_check_mark: | :white_check_mark: |
+
+> [!TIP]
+> The implementation details of PPO can be found in [this blog](https://newfacade.github.io/notes-on-reinforcement-learning/17-ppo-trl.html).
+
+## Provided Datasets
+
+<details><summary>Pre-training datasets</summary>
+
+- [Wiki Demo (en)](data/wiki_demo.txt)
+- [RefinedWeb (en)](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)
+- [RedPajama V2 (en)](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2)
+- [Wikipedia (en)](https://huggingface.co/datasets/olm/olm-wikipedia-20221220)
+- [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
+- [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)
+- [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)
+- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)
+- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
+- [CCI3-HQ (zh)](https://huggingface.co/datasets/BAAI/CCI3-HQ)
+- [CCI3-Data (zh)](https://huggingface.co/datasets/BAAI/CCI3-Data)
+- [CCI4.0-M2-Base-v1 (en&zh)](https://huggingface.co/datasets/BAAI/CCI4.0-M2-Base-v1)
+- [CCI4.0-M2-CoT-v1 (en&zh)](https://huggingface.co/datasets/BAAI/CCI4.0-M2-CoT-v1)
+- [CCI4.0-M2-Extra-v1 (en&zh)](https://huggingface.co/datasets/BAAI/CCI4.0-M2-Extra-v1)
+- [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)
+- [Infinity Instruct (zh)](https://huggingface.co/datasets/BAAI/Infinity-Instruct)
+- [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)
+- [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)
+- [DLR-Web (en)](https://huggingface.co/datasets/Attention1115/DLR-Web)
+- [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)
+- [COIG-P (zh)](https://huggingface.co/datasets/m-a-p/COIG-P)
+- [RLHF-V (en)](https://huggingface.co/datasets/openbmb/RLHF-V-Dataset)
+- [VLFeedback (en)](https://huggingface.co/datasets/Zhihui/VLFeedback)
+- [RLAIF-V (en)](https://huggingface.co/datasets/openbmb/RLAIF-V-Dataset)
+- [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
+- [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
+- [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
+- [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
+- [KTO mixed (en)](https://huggingface.co/datasets/argilla/kto-mix-15k)
+
+</details>
+
+Some datasets require confirmation before using them, so we recommend logging in with your Hugging Face account using these commands.
+
+```bash
+pip install "huggingface_hub<1.0.0"
+huggingface-cli login
+```
+
+## Requirement
+
+| Mandatory    | Minimum | Recommend |
+| ------------ | ------- | --------- |
+| python       | 3.9     | 3.10      |
+| torch        | 2.0.0   | 2.6.0     |
+| torchvision  | 0.15.0  | 0.21.0    |
+| transformers | 4.49.0  | 4.50.0    |
+| datasets     | 2.16.0  | 3.2.0     |
+| accelerate   | 0.34.0  | 1.2.1     |
+| peft         | 0.14.0  | 0.15.1    |
+| trl          | 0.8.6   | 0.9.6     |
+
+| Optional     | Minimum | Recommend |
+| ------------ | ------- | --------- |
+| CUDA         | 11.6    | 12.2      |
+| deepspeed    | 0.10.0  | 0.16.4    |
+| bitsandbytes | 0.39.0  | 0.43.1    |
+| vllm         | 0.4.3   | 0.8.2     |
+| flash-attn   | 2.5.6   | 2.7.2     |
+
+### Hardware Requirement
+
+\* *estimated*
+
+| Method                              | Bits |   7B  |  14B  |  30B  |   70B  |   `x`B  |
+| ----------------------------------- | ---- | ----- | ----- | ----- | ------ | ------- |
+| Full (`bf16` or `fp16`)             |  32  | 120GB | 240GB | 600GB | 1200GB | `18x`GB |
+| Full (`pure_bf16`)                  |  16  |  60GB | 120GB | 300GB |  600GB |  `8x`GB |
+| Freeze/LoRA/GaLore/APOLLO/BAdam/OFT |  16  |  16GB |  32GB |  64GB |  160GB |  `2x`GB |
+| QLoRA / QOFT                        |   8  |  10GB |  20GB |  40GB |   80GB |   `x`GB |
+| QLoRA / QOFT                        |   4  |   6GB |  12GB |  24GB |   48GB | `x/2`GB |
+| QLoRA / QOFT                        |   2  |   4GB |   8GB |  16GB |   24GB | `x/4`GB |
+
+## Getting Started
+
+### Installation
+
+> [!IMPORTANT]
+> Installation is mandatory.
+
+#### Install from Source
+
+```bash
+git clone --depth 1 https://github.com/hiyouga/LlamaFactory.git
+cd LlamaFactory
+pip install -e .
+pip install -r requirements/metrics.txt
+```
+
+Optional dependencies available: `metrics`, `deepspeed`. Install with: `pip install -e . && pip install -r requirements/metrics.txt -r requirements/deepspeed.txt`
+
+Additional dependencies for specific features are available in `examples/requirements/`.
+
+#### Install from Docker Image
+
+```bash
+docker run -it --rm --gpus=all --ipc=host hiyouga/llamafactory:latest
+```
+
+This image is built on Ubuntu 22.04 (x86\_64), CUDA 12.4, Python 3.11, PyTorch 2.6.0, and Flash-attn 2.7.4.
+
+Find the pre-built images: https://hub.docker.com/r/hiyouga/llamafactory/tags
+
+Please refer to [build docker](#build-docker) to build the image yourself.
+
+<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 run llamafactory-cli webui
+```
+
+</details>
+
+<details><summary>For Windows users</summary>
+
+#### Install PyTorch
+
+You need to manually install the GPU version of PyTorch on the Windows platform. Please refer to the [official website](https://pytorch.org/get-started/locally/) and the following command to install PyTorch with CUDA support:
+
+```bash
+pip uninstall torch torchvision torchaudio
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+python -c "import torch; print(torch.cuda.is_available())"
+```
+
+If you see `True` then you have successfully installed PyTorch with CUDA support.
+
+Try `dataloader_num_workers: 0` if you encounter `Can't pickle local object` error.
+
+#### 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
+```
+
+#### 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 upgrade Python to version 3.10 or higher: `pip install -r requirements/npu.txt`. Additionally, you need to install the **Ascend CANN Toolkit and Kernels**. Please follow the [installation tutorial](https://llamafactory.readthedocs.io/en/latest/advanced/npu_installation.html).
+
+
+You can also download the pre-built Docker images:
+
+```bash
+# Docker Hub
+docker pull hiyouga/llamafactory:latest-npu-a2
+docker pull hiyouga/llamafactory:latest-npu-a3
+
+# quay.io
+docker pull quay.io/ascend/llamafactory:latest-npu-a2
+docker pull quay.io/ascend/llamafactory:latest-npu-a3
+```
+
+#### 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/qwen3_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 use datasets on HuggingFace / ModelScope / Modelers hub, load the dataset in local disk, or specify a path to s3/gcs cloud storage.
+
+> [!NOTE]
+> Please update `data/dataset_info.json` to use your custom dataset.
+
+You can also use **[Easy Dataset](https://github.com/ConardLi/easy-dataset)**, **[DataFlow](https://github.com/OpenDCAI/DataFlow)** and **[GraphGen](https://github.com/open-sciencelab/GraphGen)** to create synthetic data for fine-tuning.
+
+### Quickstart
+
+Use the following 3 commands to run LoRA **fine-tuning**, **inference** and **merging** of the Qwen3-4B-Instruct model, respectively.
+
+```bash
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
+llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
+llamafactory-cli export examples/merge_lora/qwen3_lora_sft.yaml
+```
+
+See [examples/README.md](examples/README.md) for advanced usage (including distributed training).
+
+> [!TIP]
+> Use `llamafactory-cli help` to show help information.
+>
+> Read [FAQs](https://github.com/hiyouga/LLaMA-Factory/issues/4614) first if you encounter any problems.
+
+### Fine-Tuning with LLaMA Board GUI (powered by [Gradio](https://github.com/gradio-app/gradio))
+
+```bash
+llamafactory-cli webui
+```
+
+### LLaMA Factory Online
+
+Read our [documentation](https://docs.llamafactory.com.cn/docs/documents/quickstart/getstarted/?utm_source=LLaMA-Factory).
+
+### 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 PIP_INDEX=https://pypi.org/simple \
+    -t llamafactory:latest .
+
+docker run -dit --ipc=host --gpus=all \
+    -p 7860:7860 \
+    -p 8000:8000 \
+    --name llamafactory \
+    llamafactory:latest
+
+docker exec -it llamafactory bash
+```
+
+For Ascend NPU users:
+
+```bash
+docker build -f ./docker/docker-npu/Dockerfile \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    -t llamafactory:latest .
+
+docker run -dit --ipc=host \
+    -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 \
+    --name llamafactory \
+    llamafactory:latest
+
+docker exec -it llamafactory bash
+```
+
+For AMD ROCm users:
+
+```bash
+docker build -f ./docker/docker-rocm/Dockerfile \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    -t llamafactory:latest .
+
+docker run -dit --ipc=host \
+    -p 7860:7860 \
+    -p 8000:8000 \
+    --device /dev/kfd \
+    --device /dev/dri \
+    --name llamafactory \
+    llamafactory:latest
+
+docker exec -it llamafactory bash
+```
+
+</details>
+
+<details><summary>Use Docker volumes</summary>
+
+You can uncomment `VOLUME [ "/root/.cache/huggingface", "/app/shared_data", "/app/output" ]` in the Dockerfile to use data volumes.
+
+When building the Docker image, use `-v ./hf_cache:/root/.cache/huggingface` argument to mount the local directory to the container. The following data volumes are available.
+
+- `hf_cache`: Utilize Hugging Face cache on the host machine.
+- `shared_data`: The directionary to store datasets on the host machine.
+- `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/qwen3.yaml infer_backend=vllm vllm_enforce_eager=true
+```
+
+> [!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
+
+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`.
+
+### 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.
+
+```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.
+
+### 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.
+
+<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. 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. Zhang et al. CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling. ACL 2024. [[paper]](https://aclanthology.org/2024.findings-acl.830.pdf)
+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.
+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.
+1. **[WeClone](https://github.com/xming521/WeClone)**: One-stop solution for creating your digital avatar from chat logs.
+1. **[EmoLLM](https://github.com/SmartFlowAI/EmoLLM)**: A project about large language models (LLMs) and mental health.
+</details>
+
+## License
+
+This repository is licensed under the [Apache-2.0 License](LICENSE).
+
+Please follow the model licenses to use the corresponding model weights: [BLOOM](https://huggingface.co/spaces/bigscience/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) / [InternLM](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [Llama 4](https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [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) / [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) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
+
+## Citation
+
+If this work is helpful, please kindly cite as:
+
+```bibtex
+@inproceedings{zheng2024llamafactory,
+  title={LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models},
+  author={Yaowei Zheng and Richong Zhang and Junhao Zhang and Yanhan Ye and Zheyan Luo and Zhangchi Feng and Yongqiang Ma},
+  booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
+  address={Bangkok, Thailand},
+  publisher={Association for Computational Linguistics},
+  year={2024},
+  url={http://arxiv.org/abs/2403.13372}
+}
+```
+
+## Acknowledgement
+
+This repo benefits from [PEFT](https://github.com/huggingface/peft), [TRL](https://github.com/huggingface/trl), [QLoRA](https://github.com/artidoro/qlora) and [FastChat](https://github.com/lm-sys/FastChat). Thanks for their wonderful works.
+
+## Star History
+
+![Star History Chart](https://api.star-history.com/svg?repos=hiyouga/LLaMA-Factory&type=Date)

LlamaFactory/README_zh.md

@@ -0,0 +1,960 @@
+![# 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 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-1000+-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
+[![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags)
+
+[![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
+[![Discord](assets/thirdparty/discord.svg)](https://discord.gg/rKfvV9r9FK)
+[![WeChat](https://img.shields.io/badge/WeChat-User%20Group-blue?logo=wechat)](https://github.com/hiyouga/llamafactory-community)
+[![Blog](https://img.shields.io/badge/Hugo-Official%20Blog-blue?logo=hugo)](https://blog.llamafactory.net/)
+
+[![Open in Colab](assets/thirdparty/colab.svg)](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing)
+[![Open in DSW](assets/thirdparty/dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)
+[![Open in Lab4ai](assets/thirdparty/lab4ai.svg)](https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46&utm_source=LLaMA-Factory)
+[![Open in Online](assets/thirdparty/online.svg)](https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory)
+[![Open in Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board)
+[![Open in Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board)
+[![Open in Novita](https://img.shields.io/badge/Novita-Deploy%20Template-blue)](https://novita.ai/templates-library/105981?sharer=88115474-394e-4bda-968e-b88e123d0c47)
+
+### 获得[亚马逊](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)、[英伟达](https://developer.nvidia.cn/rtx/ai-toolkit)、[阿里云](https://help.aliyun.com/zh/pai/use-cases/fine-tune-a-llama-3-model-with-llama-factory)等的应用。
+
+<div align="center" markdown="1">
+
+### 赞助商 ❤️
+
+| <div style="text-align: center;"><a href="https://warp.dev/llama-factory"><img alt="Warp sponsorship" width="400" src="assets/sponsors/warp.jpg"></a><br><a href="https://warp.dev/llama-factory" style="font-size:larger;">Warp，面向开发者的智能终端</a><br><a href="https://warp.dev/llama-factory">适用于 MacOS、Linux 和 Windows</a> | <a href="https://serpapi.com"><img alt="SerpAPI sponsorship" width="250" src="assets/sponsors/serpapi.svg"> </a> |
+| ---- | ---- |
+
+----
+
+### 使用零代码[命令行](#快速开始)与 [Web UI](#llama-board-可视化微调由-gradio-驱动) 轻松微调百余种大模型
+
+![GitHub Trend](https://trendshift.io/api/badge/repositories/4535)
+
+</div>
+
+👋 加入我们的[微信群](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/main.jpg)、[NPU 用户群](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/npu.jpg)、[大模型实验室群](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/lab4ai.jpg) 或 [LLaMA Factory Online 用户群](https://github.com/hiyouga/llamafactory-community/blob/main/wechat/online.png)。
+
+\[ [English](README.md) | 中文 \]
+
+**微调大模型可以像这样轻松…**
+
+https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
+
+开始本地训练：
+- 请见[如何使用](#如何使用)
+
+开始云端训练：
+- **Colab（免费）**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing
+- **PAI-DSW（免费试用）**：https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
+- **LLaMA Factory Online（在线微调）**：https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory
+- **九章智算云（算力优惠活动）**：https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory
+
+阅读技术文档：
+- **入门教程**：https://zhuanlan.zhihu.com/p/695287607
+- **微调视频教程**：https://www.bilibili.com/video/BV1djgRzxEts/
+- **框架文档**：https://llamafactory.readthedocs.io/zh-cn/latest/
+- **框架文档（昇腾 NPU）**：https://ascend.github.io/docs/sources/llamafactory/
+- **官方博客**：https://blog.llamafactory.net/
+- **官方课程**：https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46&utm_source=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。
+
+## 目录
+
+- [项目特色](#项目特色)
+- [官方博客](#官方博客)
+- [更新日志](#更新日志)
+- [模型](#模型)
+- [训练方法](#训练方法)
+- [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)
+  - [LLaMA Factory Online 在线微调](#llama-factory-online-在线微调)
+  - [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)
+- [致谢](#致谢)
+
+## 项目特色
+
+- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen3、Qwen3-VL、DeepSeek、Gemma、GLM、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)、[APOLLO](https://github.com/zhuhanqing/APOLLO)、[Adam-mini](https://github.com/zyushun/Adam-mini)、[Muon](https://github.com/KellerJordan/Muon)、[OFT](https://github.com/huggingface/peft/tree/main/src/peft/tuners/oft)、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)、[KTransformers](https://github.com/kvcache-ai/ktransformers/)、RoPE scaling、NEFTune 和 rsLoRA。
+- **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](https://github.com/SwanHubX/SwanLab) 等等。
+- **极速推理**：基于 [vLLM](https://github.com/vllm-project/vllm) 或 [SGLang](https://github.com/sgl-project/sglang) 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        | Qwen3 / Qwen2.5-VL / Gemma 3 / GLM-4.1V / InternLM 3 / MiniCPM-o-2.6 |
+| Day 1        | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4               |
+
+## 官方博客
+
+> [!TIP]
+> 我们现在拥有了 LLaMA Factory 的专属博客！
+>
+> 网站地址：https://blog.llamafactory.net/
+
+- 💡 [KTransformers Fine-Tuning × LLaMA Factory: 用2张4090级的GPU+CPU 微调 1000B规模的超大模型](https://swcil84qspu.feishu.cn/wiki/Z1sSwb2poijybxkyPEkcDG6enVc) (中文)
+- 💡 [Easy Dataset × LLaMA Factory: 让大模型高效学习领域知识](https://buaa-act.feishu.cn/wiki/KY9xwTGs1iqHrRkjXBwcZP9WnL9)（中文）
+- [使用 LLaMA-Factory 微调心理健康大模型](https://www.lab4ai.cn/project/detail?id=25cce32ec131497b9e06a93336a0817f&type=project&utm_source=LLaMA-Factory)（中文）
+- [使用 LLaMA-Factory 构建 GPT-OSS 角色扮演模型](https://docs.llamafactory.com.cn/docs/documents/best-practice/gptroleplay/?utm_source=LLaMA-Factory)（中文）
+- [基于 LLaMA-Factory 和 EasyR1 打造一站式无代码大模型强化学习和部署平台 LLM Model Hub](https://aws.amazon.com/cn/blogs/china/building-llm-model-hub-based-on-llamafactory-and-easyr1/)（中文）
+- [通过亚马逊 SageMaker HyperPod 上的 LLaMA-Factory 增强多模态模型银行文档的视觉信息提取](https://aws.amazon.com/cn/blogs/machine-learning/how-apoidea-group-enhances-visual-information-extraction-from-banking-documents-with-multimodal-models-using-llama-factory-on-amazon-sagemaker-hyperpod/)（英文）
+
+<details><summary>全部博客</summary>
+
+- [使用 LLaMA-Factory 微调 Llama3.1-70B 医学诊断模型](https://docs.alayanew.com/docs/documents/bestPractice/bigModel/llama70B/?utm_source=LLaMA-Factory)（中文）
+- [使用 LLaMA-Factory 微调 Qwen2.5-VL 实现自动驾驶场景微调](https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory)（中文）
+- [LLaMA Factory：微调 DeepSeek-R1-Distill-Qwen-7B 模型实现新闻标题分类器](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b)（中文）
+- [基于 Amazon SageMaker 和 LLaMA-Factory 打造一站式无代码模型微调部署平台 Model Hub](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)（中文）
+- [LLaMA Factory 多模态微调实践：微调 Qwen2-VL 构建文旅大模型](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl)（中文）
+- [LLaMA Factory：微调 Llama3 模型实现角色扮演](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory)（中文）
+
+</details>
+
+## 更新日志
+
+[25/10/26] 我们支持了Megatron-core作为训练后端和适配了[**mcore_adapter**](https://github.com/alibaba/ROLL/tree/main/mcore_adapter)。查看[PR #9237](https://github.com/hiyouga/LLaMA-Factory/pull/9237)以使用。
+
+[25/08/22] 我们支持了 **[OFT](https://arxiv.org/abs/2306.07280)** 和 **[OFTv2](https://arxiv.org/abs/2506.19847)** 模型的微调。查看 [examples](examples/README.md) 以使用。
+
+[25/08/20] 我们支持了 **[Intern-S1-mini](https://huggingface.co/internlm/Intern-S1-mini)** 模型的微调。查看 [PR #8976](https://github.com/hiyouga/LLaMA-Factory/pull/8976) 以使用。
+
+[25/08/06] 我们支持了 **[GPT-OSS](https://github.com/openai/gpt-oss)** 模型的微调。查看 [PR #8826](https://github.com/hiyouga/LLaMA-Factory/pull/8826) 以使用。
+
+<details><summary>展开日志</summary>
+
+[25/07/02] 我们支持了 **[GLM-4.1V-9B-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)** 模型的微调。
+
+[25/04/28] 我们支持了 **[Qwen3](https://qwenlm.github.io/blog/qwen3/)** 系列模型的微调。
+
+[25/04/21] 我们支持了 **[Muon](https://github.com/KellerJordan/Muon)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@tianshijing](https://github.com/tianshijing) 的 PR。
+
+[25/04/16] 我们支持了 **[InternVL3](https://huggingface.co/OpenGVLab/InternVL3-8B)** 模型的微调。查看 [PR #7258](https://github.com/hiyouga/LLaMA-Factory/pull/7258) 以使用。
+
+[25/04/14] 我们支持了 **[GLM-Z1](https://huggingface.co/THUDM/GLM-Z1-9B-0414)** 和 **[Kimi-VL](https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct)** 模型的微调。
+
+[25/04/06] 我们支持了 **[Llama 4](https://ai.meta.com/blog/llama-4-multimodal-intelligence/)** 模型的微调。查看 [PR #7611](https://github.com/hiyouga/LLaMA-Factory/pull/7611) 以使用。
+
+[25/03/31] 我们支持了 **[Qwen2.5 Omni](https://qwenlm.github.io/blog/qwen2.5-omni/)** 模型的微调。查看 [PR #7537](https://github.com/hiyouga/LLaMA-Factory/pull/7537) 以使用。
+
+[25/03/15] 我们支持了 **[SGLang](https://github.com/sgl-project/sglang)** 推理后端，请使用 `infer_backend: sglang` 启用。
+
+[25/03/12] 我们支持了 **[Gemma 3](https://huggingface.co/blog/gemma3)** 模型的微调。
+
+[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。
+
+[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 **[InternLM 3](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。
+
+[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。
+
+[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 `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)。
+
+[24/05/14] 我们支持了昇腾 NPU 设备的训练和推理。详情请查阅[安装](#安装-llama-factory)部分。
+
+[24/04/26] 我们支持了多模态模型 **LLaVA-1.5** 的微调。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/04/22] 我们提供了在免费 T4 GPU 上微调 Llama-3 模型的 **[Colab 笔记本](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing)**。Hugging Face 社区公开了两个利用 LLaMA Factory 微调的 Llama-3 模型，详情请见 [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) 和 [Llama3-Chinese](https://huggingface.co/zhichen/Llama3-Chinese)。
+
+[24/04/21] 我们基于 [AstraMindAI 的仓库](https://github.com/astramind-ai/Mixture-of-depths)支持了 **[混合深度训练](https://arxiv.org/abs/2404.02258)**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/04/16] 我们支持了 **[BAdam](https://arxiv.org/abs/2404.02827)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/04/16] 我们支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的长序列训练（24GB 可训练 Llama-2-7B-56k）。该方法相比 FlashAttention-2 提供了 **117%** 的训练速度和 **50%** 的显存节约。更多数据请见[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
+
+[24/03/31] 我们支持了 **[ORPO](https://arxiv.org/abs/2403.07691)**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/03/21] 我们的论文 "[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)" 可在 arXiv 上查看！
+
+[24/03/20] 我们支持了能在 2x24GB GPU 上微调 70B 模型的 **FSDP+QLoRA**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/03/13] 我们支持了 **[LoRA+](https://arxiv.org/abs/2402.12354)**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/03/07] 我们支持了 **[GaLore](https://arxiv.org/abs/2403.03507)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/03/07] 我们集成了 **[vLLM](https://github.com/vllm-project/vllm)** 以实现极速并发推理。请使用 `infer_backend: vllm` 来获得 **270%** 的推理速度。
+
+[24/02/28] 我们支持了 **[DoRA](https://arxiv.org/abs/2402.09353)** 微调。请使用 `use_dora: true` 参数进行 DoRA 微调。
+
+[24/02/15] 我们支持了 [LLaMA Pro](https://github.com/TencentARC/LLaMA-Pro) 提出的**块扩展**方法。详细用法请参照 [examples](examples/README_zh.md)。
+
+[24/02/05] Qwen1.5（Qwen2 测试版）系列模型已在 LLaMA-Factory 中实现微调支持。详情请查阅该[博客页面](https://qwenlm.github.io/zh/blog/qwen1.5/)。
+
+[24/01/18] 我们针对绝大多数模型实现了 **Agent 微调**，微调时指定 `dataset: glaive_toolcall_zh` 即可使模型获得工具调用能力。
+
+[23/12/23] 我们针对 LLaMA, Mistral 和 Yi 模型支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的 LoRA 训练加速。请使用 `use_unsloth: true` 参数启用 unsloth 优化。该方法可提供 **170%** 的训练速度，详情请查阅[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。
+
+[23/12/12] 我们支持了微调最新的混合专家模型 **[Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)**。硬件需求请查阅[此处](#硬件依赖)。
+
+[23/12/01] 我们支持了从 **[魔搭社区](https://modelscope.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔搭社区下载)。
+
+[23/10/21] 我们支持了 **[NEFTune](https://arxiv.org/abs/2310.05914)** 训练技巧。请使用 `neftune_noise_alpha: 5` 参数启用 NEFTune。
+
+[23/09/27] 我们针对 LLaMA 模型支持了 [LongLoRA](https://github.com/dvlab-research/LongLoRA) 提出的 **$S^2$-Attn**。请使用 `shift_attn: true` 参数以启用该功能。
+
+[23/09/23] 我们在项目中集成了 MMLU、C-Eval 和 CMMLU 评估集。详细用法请参照 [examples](examples/README_zh.md)。
+
+[23/09/10] 我们支持了 **[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)**。如果您使用的是 RTX4090、A100 或 H100 GPU，请使用 `flash_attn: fa2` 参数以启用 FlashAttention-2。
+
+[23/08/12] 我们支持了 **RoPE 插值**来扩展 LLaMA 模型的上下文长度。请使用 `rope_scaling: linear` 参数训练模型或使用 `rope_scaling: dynamic` 参数评估模型。
+
+[23/08/11] 我们支持了指令模型的 **[DPO 训练](https://arxiv.org/abs/2305.18290)**。详细用法请参照 [examples](examples/README_zh.md)。
+
+[23/07/31] 我们支持了**数据流式加载**。请使用 `streaming: true` 和 `max_steps: 10000` 参数来流式加载数据集。
+
+[23/07/29] 我们在 Hugging Face 发布了两个 13B 指令微调模型。详细内容请查阅我们的 Hugging Face 项目（[LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/Baichuan-13B-sft)）。
+
+[23/07/18] 我们开发了支持训练和测试的**浏览器一体化界面**。请使用 `train_web.py` 在您的浏览器中微调模型。感谢 [@KanadeSiina](https://github.com/KanadeSiina) 和 [@codemayq](https://github.com/codemayq) 在该功能开发中付出的努力。
+
+[23/07/09] 我们开源了 **[FastEdit](https://github.com/hiyouga/FastEdit)** ⚡🩹，一个简单易用的、能迅速编辑大模型事实记忆的工具包。如果您感兴趣请关注我们的 [FastEdit](https://github.com/hiyouga/FastEdit) 项目。
+
+[23/06/29] 我们提供了一个**可复现的**指令模型微调示例，详细内容请查阅 [Baichuan-7B-sft](https://huggingface.co/hiyouga/Baichuan-7B-sft)。
+
+[23/06/22] 我们对齐了[示例 API](src/api_demo.py) 与 [OpenAI API](https://platform.openai.com/docs/api-reference/chat) 的格式，您可以将微调模型接入**任意基于 ChatGPT 的应用**中。
+
+[23/06/03] 我们实现了 4 比特的 LoRA 训练（也称 **[QLoRA](https://github.com/artidoro/qlora)**）。详细用法请参照 [examples](examples/README_zh.md)。
+
+</details>
+
+> [!TIP]
+> 如果您无法使用最新的功能，请尝试重新拉取代码并再次安装 LLaMA-Factory。
+
+## 模型
+
+| 模型名                                                             | 参数量                            | Template             |
+| ----------------------------------------------------------------- | -------------------------------- | -------------------- |
+| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                    |
+| [DeepSeek (LLM/Code/MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | deepseek             |
+| [DeepSeek 3-3.2](https://huggingface.co/deepseek-ai)              | 236B/671B                        | deepseek3            |
+| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai)       | 1.5B/7B/8B/14B/32B/70B/671B      | deepseekr1           |
+| [ERNIE-4.5](https://huggingface.co/baidu)                         | 0.3B/21B/300B                    | ernie_nothink        |
+| [Falcon/Falcon H1](https://huggingface.co/tiiuae)                 | 0.5B/1.5B/3B/7B/11B/34B/40B/180B | falcon/falcon_h1     |
+| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma/gemma2         |
+| [Gemma 3/Gemma 3n](https://huggingface.co/google)                 | 270M/1B/4B/6B/8B/12B/27B         | gemma3/gemma3n       |
+| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/zai-org)         | 9B/32B                           | glm4/glmz1           |
+| [GLM-4.5/GLM-4.5(6)V](https://huggingface.co/zai-org)             | 9B/106B/355B                     | glm4_moe/glm4_5v     |
+| [GPT-2](https://huggingface.co/openai-community)                  | 0.1B/0.4B/0.8B/1.5B              | -                    |
+| [GPT-OSS](https://huggingface.co/openai)                          | 20B/120B                         | gpt_oss              |
+| [Granite 3-4](https://huggingface.co/ibm-granite)                 | 1B/2B/3B/7B/8B                   | granite3/granite4    |
+| [Hunyuan/Hunyuan1.5 (MT)](https://huggingface.co/tencent/)        | 0.5B/1.8B/4B/7B/13B              | hunyuan/hunyuan_small |
+| [InternLM 2-3](https://huggingface.co/internlm)                   | 7B/8B/20B                        | intern2              |
+| [InternVL 2.5-3.5](https://huggingface.co/OpenGVLab)              | 1B/2B/4B/8B/14B/30B/38B/78B/241B | intern_vl            |
+| [Intern-S1-mini](https://huggingface.co/internlm/)                | 8B                               | intern_s1            |
+| [Kimi-VL](https://huggingface.co/moonshotai)                      | 16B                              | kimi_vl              |
+| [Ling 2.0 (mini/flash)](https://huggingface.co/inclusionAI)       | 16B/100B                         | bailing_v2           |
+| [LFM 2.5 (VL)](https://huggingface.co/LiquidAI)                   | 1.2B/1.6B                        | lfm2/lfm2_vl         |
+| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -                    |
+| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2               |
+| [Llama 3-3.3](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3               |
+| [Llama 4](https://huggingface.co/meta-llama)                      | 109B/402B                        | llama4               |
+| [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     |
+| [MiMo](https://huggingface.co/XiaomiMiMo)                         | 7B/309B                          | mimo/mimo_v2         |
+| [MiniCPM 4](https://huggingface.co/openbmb)                       | 0.5B/8B                          | cpm4                 |
+| [MiniCPM-o-2.6/MiniCPM-V-2.6](https://huggingface.co/openbmb)     | 8B                               | minicpm_o/minicpm_v  |
+| [MiniMax-M1/MiniMax-M2](https://huggingface.co/MiniMaxAI/models)  | 229B/456B                        | minimax1/minimax2    |
+| [Ministral 3](https://huggingface.co/mistralai)                   | 3B/8B/14B                        | ministral3           |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral              |
+| [PaliGemma/PaliGemma2](https://huggingface.co/google)             | 3B/10B/28B                       | paligemma            |
+| [Phi-3/Phi-3.5](https://huggingface.co/microsoft)                 | 4B/14B                           | phi                  |
+| [Phi-3-small](https://huggingface.co/microsoft)                   | 7B                               | phi_small            |
+| [Phi-4-mini/Phi-4](https://huggingface.co/microsoft)              | 3.8B/14B                         | phi4_mini/phi4       |
+| [Pixtral](https://huggingface.co/mistralai)                       | 12B                              | pixtral              |
+| [Qwen2 (Code/Math/MoE/QwQ)](https://huggingface.co/Qwen)          | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen                 |
+| [Qwen3 (MoE/Instruct/Thinking/Next)](https://huggingface.co/Qwen) | 0.6B/1.7B/4B/8B/14B/32B/80B/235B | qwen3/qwen3_nothink  |
+| [Qwen2-Audio](https://huggingface.co/Qwen)                        | 7B                               | qwen2_audio          |
+| [Qwen2.5-Omni](https://huggingface.co/Qwen)                       | 3B/7B                            | qwen2_omni           |
+| [Qwen3-Omni](https://huggingface.co/Qwen)                         | 30B                              | qwen3_omni           |
+| [Qwen2-VL/Qwen2.5-VL/QVQ](https://huggingface.co/Qwen)            | 2B/3B/7B/32B/72B                 | qwen2_vl             |
+| [Qwen3-VL](https://huggingface.co/Qwen)                           | 2B/4B/8B/30B/32B/235B            | qwen3_vl             |
+| [Seed (OSS/Coder)](https://huggingface.co/ByteDance-Seed)         | 8B/36B                           | seed_oss/seed_coder  |
+| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                    |
+| [TeleChat 2-2.5](https://huggingface.co/Tele-AI)                  | 3B/7B/35B/115B                   | telechat2            |
+| [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**。
+>
+> 如果模型有推理 / 非推理两个版本，请使用 `_nothink` 后缀来区分不同的模板。例如 `qwen3` 和 `qwen3_nothink`。
+>
+> 请务必在训练和推理时采用**完全一致**的模板。
+>
+> \*：您需要从 main 分支安装 `transformers` 并使用 `DISABLE_VERSION_CHECK=1` 来跳过版本检查。
+>
+> \*\*：您需要安装特定版本的 `transformers` 以使用该模型。
+
+项目所支持模型的完整列表请参阅 [constants.py](src/llamafactory/extras/constants.py)。
+
+您也可以在 [template.py](src/llamafactory/data/template.py) 中添加自己的对话模板。
+
+## 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: |
+| PPO 训练               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| DPO 训练               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| KTO 训练               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| ORPO 训练              | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+| SimPO 训练             | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+
+> [!TIP]
+> 有关 PPO 的实现细节，请参考[此博客](https://newfacade.github.io/notes-on-reinforcement-learning/17-ppo-trl.html)。
+
+## 数据集
+
+<details><summary>预训练数据集</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)
+- [CCI3-HQ (zh)](https://huggingface.co/datasets/BAAI/CCI3-HQ)
+- [CCI3-Data (zh)](https://huggingface.co/datasets/BAAI/CCI3-Data)
+- [CCI4.0-M2-Base-v1 (en&zh)](https://huggingface.co/datasets/BAAI/CCI4.0-M2-Base-v1)
+- [CCI4.0-M2-CoT-v1 (en&zh)](https://huggingface.co/datasets/BAAI/CCI4.0-M2-CoT-v1)
+- [CCI4.0-M2-Extra-v1 (en&zh)](https://huggingface.co/datasets/BAAI/CCI4.0-M2-Extra-v1)
+- [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)
+- [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)
+
+</details>
+
+<details><summary>指令微调数据集</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)
+- [Infinity Instruct (zh)](https://huggingface.co/datasets/BAAI/Infinity-Instruct)
+- [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)
+- [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)
+- [DLR-Web (en)](https://huggingface.co/datasets/Attention1115/DLR-Web)
+- [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>偏好数据集</summary>
+
+- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
+- [COIG-P (zh)](https://huggingface.co/datasets/m-a-p/COIG-P)
+- [RLHF-V (en)](https://huggingface.co/datasets/openbmb/RLHF-V-Dataset)
+- [VLFeedback (en)](https://huggingface.co/datasets/Zhihui/VLFeedback)
+- [RLAIF-V (en)](https://huggingface.co/datasets/openbmb/RLAIF-V-Dataset)
+- [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>
+
+部分数据集的使用需要确认，我们推荐使用下述命令登录您的 Hugging Face 账户。
+
+```bash
+pip install --upgrade huggingface_hub
+huggingface-cli login
+```
+
+## 软硬件依赖
+
+| 必需项        | 至少     | 推荐      |
+| ------------ | ------- | --------- |
+| python       | 3.9     | 3.10      |
+| torch        | 2.0.0   | 2.6.0     |
+| torchvision  | 0.15.0  | 0.21.0    |
+| transformers | 4.49.0  | 4.50.0    |
+| datasets     | 2.16.0  | 3.2.0     |
+| accelerate   | 0.34.0  | 1.2.1     |
+| peft         | 0.14.0  | 0.15.1    |
+| trl          | 0.8.6   | 0.9.6     |
+
+| 可选项        | 至少     | 推荐      |
+| ------------ | ------- | --------- |
+| CUDA         | 11.6    | 12.2      |
+| deepspeed    | 0.10.0  | 0.16.4    |
+| bitsandbytes | 0.39.0  | 0.43.1    |
+| vllm         | 0.4.3   | 0.8.2     |
+| flash-attn   | 2.5.6   | 2.7.2     |
+
+### 硬件依赖
+
+\* *估算值*
+
+| 方法                             | 精度 |   7B  |  14B  |  30B  |   70B  |   `x`B  |
+| ------------------------------- | ---- | ----- | ----- | ----- | ------ | ------- |
+| Full (`bf16` or `fp16`)         |  32  | 120GB | 240GB | 600GB | 1200GB | `18x`GB |
+| Full (`pure_bf16`)              |  16  |  60GB | 120GB | 300GB |  600GB |  `8x`GB |
+| Freeze/LoRA/GaLore/APOLLO/BAdam |  16  |  16GB |  32GB |  64GB |  160GB |  `2x`GB |
+| QLoRA                           |   8  |  10GB |  20GB |  40GB |   80GB |   `x`GB |
+| QLoRA                           |   4  |   6GB |  12GB |  24GB |   48GB | `x/2`GB |
+| QLoRA                           |   2  |   4GB |   8GB |  16GB |   24GB | `x/4`GB |
+
+## 如何使用
+
+### 安装 LLaMA Factory
+
+> [!IMPORTANT]
+> 此步骤为必需。
+
+#### 从源码安装
+
+```bash
+git clone --depth 1 https://github.com/hiyouga/LlamaFactory.git
+cd LlamaFactory
+pip install -e .
+pip install -r requirements/metrics.txt
+```
+
+可选的额外依赖项：`metrics`、`deepspeed`。使用 `pip install -e . && pip install -r requirements/metrics.txt -r requirements/deepspeed.txt` 安装。
+
+其他可选依赖项请参考 `examples/requirements/` 目录下的文件。
+
+#### 从镜像安装
+
+```bash
+docker run -it --rm --gpus=all --ipc=host hiyouga/llamafactory:latest
+```
+
+该镜像基于 Ubuntu 22.04（x86\_64）、CUDA 12.4、Python 3.11、PyTorch 2.6.0 和 Flash-attn 2.7.4 构建。
+
+查看全部镜像：https://hub.docker.com/r/hiyouga/llamafactory/tags
+
+请参阅[构建 Docker](#构建-docker) 来重新构建镜像。
+
+<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 run llamafactory-cli webui
+```
+
+</details>
+
+<details><summary>Windows 用户指南</summary>
+
+#### 安装 PyTorch
+
+Windows 平台需要额外手动安装 GPU 版本的 PyTorch 依赖包，您可以参考[官方网站](https://pytorch.org/get-started/locally/)和以下命令安装并测试 PyTorch 是否正确安装。
+
+```bash
+pip uninstall torch torchvision torchaudio
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+python -c "import torch; print(torch.cuda.is_available())"
+```
+
+如果看到 `True` 则说明安装成功。
+
+若遇到类似 `Can't pickle local object` 的报错，请设置 `dataloader_num_workers: 0`。
+
+#### 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
+```
+
+#### 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，请升级 Python 到 3.10 及以上，并需要指定额外依赖项，使用 `pip install -r requirements/npu.txt` 命令安装。此外，还需要安装 **Ascend CANN Toolkit 与 Kernels**，安装方法请参考[安装教程](https://llamafactory.readthedocs.io/zh-cn/latest/advanced/npu_installation.html)。
+
+您可以直接下载预安装的最新docker镜像：
+
+```bash
+# Docker Hub
+docker pull hiyouga/llamafactory:latest-npu-a2
+docker pull hiyouga/llamafactory:latest-npu-a3
+
+# quay.io
+docker pull quay.io/ascend/llamafactory:latest-npu-a2
+docker pull quay.io/ascend/llamafactory:latest-npu-a3
+```
+
+#### 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/qwen3_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 / 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。
+
+您也可以使用 **[Easy Dataset](https://github.com/ConardLi/easy-dataset)**、**[DataFlow](https://github.com/OpenDCAI/DataFlow)** 和 **[GraphGen](https://github.com/open-sciencelab/GraphGen)** 构建用于微调的合成数据。
+
+### 快速开始
+
+下面三行命令分别对 Qwen3-4B-Instruct 模型进行 LoRA **微调**、**推理**和**合并**。
+
+```bash
+llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
+llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
+llamafactory-cli export examples/merge_lora/qwen3_lora_sft.yaml
+```
+
+高级用法请参考 [examples/README_zh.md](examples/README_zh.md)（包括多 GPU 微调）。
+
+> [!TIP]
+> 使用 `llamafactory-cli help` 显示帮助信息。
+>
+> 遇到报错请先看[常见���题](https://github.com/hiyouga/LLaMA-Factory/issues/4614)。
+
+### LLaMA Board 可视化微调（由 [Gradio](https://github.com/gradio-app/gradio) 驱动）
+
+```bash
+llamafactory-cli webui
+```
+
+### LLaMA Factory Online 在线微调
+
+详情阅读该[文档](https://docs.llamafactory.com.cn/docs/documents/quickstart/getstarted/?utm_source=LLaMA-Factory)。
+
+### 构建 Docker
+
+CUDA 用户：
+
+```bash
+cd docker/docker-cuda/
+docker compose up -d
+docker compose exec llamafactory bash
+```
+
+昇腾 NPU 用户：
+
+```bash
+cd docker/docker-npu/
+docker compose up -d
+docker compose exec llamafactory bash
+```
+
+AMD ROCm 用户：
+
+```bash
+cd docker/docker-rocm/
+docker compose up -d
+docker compose exec llamafactory bash
+```
+
+<details><summary>不使用 Docker Compose 构建</summary>
+
+CUDA 用户：
+
+```bash
+docker build -f ./docker/docker-cuda/Dockerfile \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    --build-arg EXTRAS=metrics \
+    -t llamafactory:latest .
+
+docker run -dit --ipc=host --gpus=all \
+    -p 7860:7860 \
+    -p 8000:8000 \
+    --name llamafactory \
+    llamafactory:latest
+
+docker exec -it llamafactory bash
+```
+
+昇腾 NPU 用户：
+
+```bash
+docker build -f ./docker/docker-npu/Dockerfile \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    --build-arg EXTRAS=torch-npu,metrics \
+    -t llamafactory:latest .
+
+docker run -dit --ipc=host \
+    -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 \
+    --name llamafactory \
+    llamafactory:latest
+
+docker exec -it llamafactory bash
+```
+
+AMD ROCm 用户：
+
+```bash
+docker build -f ./docker/docker-rocm/Dockerfile \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    --build-arg EXTRAS=metrics \
+    -t llamafactory:latest .
+
+docker run -dit --ipc=host \
+    -p 7860:7860 \
+    -p 8000:8000 \
+    --device /dev/kfd \
+    --device /dev/dri \
+    --name llamafactory \
+    llamafactory:latest
+
+docker exec -it llamafactory bash
+```
+
+</details>
+
+<details><summary>使用数据卷</summary>
+
+您可以通过移除 Dockerfile 中 `VOLUME [ "/root/.cache/huggingface", "/app/shared_data", "/app/output" ]` 的注释来使用数据卷。
+
+在构建 Docker 时使用参数 `-v ./hf_cache:/root/.cache/huggingface` 来挂载数据卷。各个数据卷的含义表示如下。
+
+- `hf_cache`：使用宿主机的 Hugging Face 缓存文件夹。
+- `shared_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。
+
+</details>
+
+### 利用 vLLM 部署 OpenAI API
+
+```bash
+API_PORT=8000 llamafactory-cli api examples/inference/qwen3.yaml infer_backend=vllm vllm_enforce_eager=true
+```
+
+> [!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
+
+如果您在 Hugging Face 模型和数据集的下载中遇到了问题，可以通过下述方法使用魔搭社区。
+
+```bash
+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。
+
+```yaml
+report_to: wandb
+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 ���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。
+
+<details><summary>点击显示</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. 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. **[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。
+1. **[WeClone](https://github.com/xming521/WeClone)**：从聊天记录创造数字分身的一站式解决方案。
+
+</details>
+
+## 协议
+
+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：[BLOOM](https://huggingface.co/spaces/bigscience/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) / [InternLM](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [Llama 4](https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [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) / [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) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan)
+
+## 引用
+
+如果您觉得此项目有帮助，请考虑以下列格式引用
+
+```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}
+}
+```
+
+## 致谢
+
+本项目受益于 [PEFT](https://github.com/huggingface/peft)、[TRL](https://github.com/huggingface/trl)、[QLoRA](https://github.com/artidoro/qlora) 和 [FastChat](https://github.com/lm-sys/FastChat)，感谢以上诸位作者的付出。
+
+## Star History
+
+![Star History Chart](https://api.star-history.com/svg?repos=hiyouga/LLaMA-Factory&type=Date)

LlamaFactory/pyproject.toml

@@ -0,0 +1,149 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "llamafactory"
+dynamic = ["version"]
+description = "Unified Efficient Fine-Tuning of 100+ LLMs"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.11.0"
+authors = [
+    { name = "hiyouga", email = "hiyouga@buaa.edu.cn" }
+]
+keywords = [
+    "AI",
+    "LLM",
+    "GPT",
+    "ChatGPT",
+    "Llama",
+    "Transformer",
+    "DeepSeek",
+    "Pytorch"
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence"
+]
+dependencies = [
+    # core deps
+    "torch>=2.4.0",
+    "torchvision>=0.19.0",
+    "torchaudio>=2.4.0",
+    "transformers>=4.51.0,<=5.0.0,!=4.52.0,!=4.57.0",
+    "datasets>=2.16.0,<=4.0.0",
+    "accelerate>=1.3.0,<=1.11.0",
+    "peft>=0.18.0,<=0.18.1",
+    "trl>=0.18.0,<=0.24.0",
+    "torchdata>=0.10.0,<=0.11.0",
+    # gui
+    "gradio>=4.38.0,<=5.50.0",
+    "matplotlib>=3.7.0",
+    "tyro<0.9.0",
+    # ops
+    "einops",
+    "numpy",
+    "pandas",
+    "scipy",
+    # model and tokenizer
+    "sentencepiece",
+    "tiktoken",
+    "modelscope",
+    "hf-transfer",
+    "safetensors",
+    # python
+    "av>=10.0.0,<=16.0.0",
+    "fire",
+    "omegaconf",
+    "packaging",
+    "protobuf",
+    "pyyaml",
+    "pydantic",
+    # api
+    "uvicorn",
+    "fastapi",
+    "sse-starlette",
+]
+
+[project.scripts]
+llamafactory-cli = "llamafactory.cli:main"
+lmf = "llamafactory.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/hiyouga/LLaMA-Factory"
+Repository = "https://github.com/hiyouga/LLaMA-Factory"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/llamafactory"]
+
+[tool.hatch.version]
+path = "src/llamafactory/extras/env.py"
+pattern = "VERSION = \"(?P<version>[^\"]+)\""
+
+[tool.ruff]
+target-version = "py311"
+line-length = 119
+indent-width = 4
+
+[tool.ruff.lint]
+ignore = [
+    "C408",  # collection
+    "C901",  # complex
+    "E501",  # line too long
+    "E731",  # lambda function
+    "E741",  # ambiguous var name
+    "UP007", # no upgrade union
+    "UP045", # no upgrade optional
+    "D100",  # no doc public module
+    "D101",  # no doc public class
+    "D102",  # no doc public method
+    "D103",  # no doc public function
+    "D104",  # no doc public package
+    "D105",  # no doc magic method
+    "D107",  # no doc __init__
+]
+extend-select = [
+    "C",      # complexity
+    "E",      # error
+    "F",      # pyflakes
+    "I",      # isort
+    "W",      # warning
+    "UP",     # pyupgrade
+    "D",      # pydocstyle
+    "PT009",  # pytest assert
+    "RUF022", # sort __all__
+]
+
+[tool.ruff.lint.isort]
+lines-after-imports = 2
+known-first-party = ["llamafactory"]
+known-third-party = [
+    "accelerate",
+    "datasets",
+    "gradio",
+    "numpy",
+    "peft",
+    "torch",
+    "transformers",
+    "trl",
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+docstring-code-format = true
+skip-magic-trailing-comma = false
+line-ending = "auto"

LlamaFactory/wandb/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2026-02-11T03:55:40.10138239Z","level":"INFO","msg":"stream: starting","core version":"0.24.2"}
+{"time":"2026-02-11T03:55:40.456868425Z","level":"INFO","msg":"stream: created new stream","id":"7vgn4sn5"}
+{"time":"2026-02-11T03:55:40.457669418Z","level":"INFO","msg":"handler: started","stream_id":"7vgn4sn5"}
+{"time":"2026-02-11T03:55:40.460178531Z","level":"INFO","msg":"stream: started","id":"7vgn4sn5"}
+{"time":"2026-02-11T03:55:40.460254263Z","level":"INFO","msg":"writer: started","stream_id":"7vgn4sn5"}
+{"time":"2026-02-11T03:55:40.460285384Z","level":"INFO","msg":"sender: started","stream_id":"7vgn4sn5"}
+{"time":"2026-02-11T23:24:56.274798427Z","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/markmochi200-linksome-ai/llamafactory/7vgn4sn5/file_stream","body":"\n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>502 Server Error</title>\n</head>\n<body text=#000000 bgcolor=#ffffff>\n<h1>Error: Server Error</h1>\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\n<h2></h2>\n</body></html>\n"}
+{"time":"2026-02-12T10:15:26.287337035Z","level":"INFO","msg":"stream: closing","id":"7vgn4sn5"}

LlamaFactory/wandb/debug.log

@@ -0,0 +1,350 @@
+2026-02-11 03:55:39,847 INFO    MainThread:874 [wandb_setup.py:_flush():81] Current SDK version is 0.24.2
+2026-02-11 03:55:39,847 INFO    MainThread:874 [wandb_setup.py:_flush():81] Configure stats pid to 874
+2026-02-11 03:55:39,848 INFO    MainThread:874 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-02-11 03:55:39,849 INFO    MainThread:874 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /workspace/LlamaFactory/wandb/run-20260211_035539-7vgn4sn5/logs/debug.log
+2026-02-11 03:55:39,850 INFO    MainThread:874 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /workspace/LlamaFactory/wandb/run-20260211_035539-7vgn4sn5/logs/debug-internal.log
+2026-02-11 03:55:39,851 INFO    MainThread:874 [wandb_init.py:init():844] calling init triggers
+2026-02-11 03:55:39,852 INFO    MainThread:874 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-02-11 03:55:39,852 INFO    MainThread:874 [wandb_init.py:init():892] starting backend
+2026-02-11 03:55:40,085 INFO    MainThread:874 [wandb_init.py:init():895] sending inform_init request
+2026-02-11 03:55:40,096 INFO    MainThread:874 [wandb_init.py:init():903] backend started and connected
+2026-02-11 03:55:40,100 INFO    MainThread:874 [wandb_init.py:init():973] updated telemetry
+2026-02-11 03:55:40,181 INFO    MainThread:874 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-02-11 03:55:40,895 INFO    MainThread:874 [wandb_init.py:init():1042] starting run threads in backend
+2026-02-11 03:55:41,100 INFO    MainThread:874 [wandb_run.py:_console_start():2529] atexit reg
+2026-02-11 03:55:41,100 INFO    MainThread:874 [wandb_run.py:_redirect():2377] redirect: wrap_raw
+2026-02-11 03:55:41,101 INFO    MainThread:874 [wandb_run.py:_redirect():2446] Wrapping output streams.
+2026-02-11 03:55:41,101 INFO    MainThread:874 [wandb_run.py:_redirect():2469] Redirects installed.
+2026-02-11 03:55:41,110 INFO    MainThread:874 [wandb_init.py:init():1082] run started, returning control to user process
+2026-02-11 03:55:41,113 INFO    MainThread:874 [wandb_run.py:_config_callback():1404] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': '/workspace/Qwen/Qwen3-8B-Base', 'revision': None, 'inference_mode': False, 'r': 32, 'target_modules': ['q_proj', 'v_proj', 'down_proj', 'up_proj', 'gate_proj', 'k_proj', 'o_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.03, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False}}, 'vocab_size': 151936, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 12288, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 36, 'num_key_value_heads': 8, 'head_dim': 128, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_bias': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'pad_token_id': 151643, 'bos_token_id': None, 'eos_token_id': 151645, 'tie_word_embeddings': False, 'rope_parameters': {'rope_theta': 1000000, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'architectures': ['Qwen3ForCausalLM'], 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, '_name_or_path': '/workspace/Qwen/Qwen3-8B-Base', 'transformers_version': '5.0.0', 'model_type': 'qwen3', 'output_attentions': False, 'output_dir': '/workspace/v127rc_exp2/B_mup', 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0001, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1, 'num_train_epochs': 10, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.01, 'warmup_steps': 0.01, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': None, 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 100, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'save_on_each_node': False, 'save_only_model': True, 'restore_callback_states_from_checkpoint': False, 'use_cpu': False, 'seed': 42, 'data_seed': None, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': -1, 'ddp_backend': None, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': ['labels'], 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'auto_find_batch_size': False, 'full_determinism': False, 'ddp_timeout': 180000000, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_num_input_tokens_seen': 'all', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True, 'sortish_sampler': False, 'predict_with_generate': False, 'generation_max_length': 2047, 'generation_num_beams': None, 'generation_config': None, 'ray_num_workers': 1, 'ray_init_kwargs': None, 'master_addr': None, 'master_port': None, 'fp8': False, 'fp8_backend': 'auto', 'fp8_enable_fsdp_float8_all_gather': False, 'overwrite_output_dir': False}
+2026-02-11 03:55:41,128 INFO    MainThread:874 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 8278029312 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7c8cb14f5050>>
+2026-02-11 03:55:41,128 INFO    MainThread:874 [wandb_run.py:_config_callback():1404] config_cb model/num_parameters 8278029312 None
+2026-02-11 03:55:41,133 INFO    MainThread:874 [wandb_run.py:_config_callback():1404] config_cb None None {'model_args': {'model_name_or_path': '/workspace/Qwen/Qwen3-8B-Base', 'adapter_name_or_path': None, 'adapter_folder': None, 'cache_dir': None, 'use_fast_tokenizer': True, 'resize_vocab': False, 'split_special_tokens': False, 'add_tokens': None, 'add_special_tokens': None, 'new_special_tokens_config': None, 'init_special_tokens': 'noise_init', 'model_revision': 'main', 'low_cpu_mem_usage': True, 'rope_scaling': None, 'flash_attn': 'auto', 'shift_attn': False, 'mixture_of_depths': None, 'use_unsloth': False, 'use_unsloth_gc': False, 'enable_liger_kernel': False, 'moe_aux_loss_coef': None, 'disable_gradient_checkpointing': False, 'use_reentrant_gc': True, 'upcast_layernorm': False, 'upcast_lmhead_output': False, 'train_from_scratch': False, 'infer_backend': 'HF', 'offload_folder': 'offload', 'use_kv_cache': True, 'use_v1_kernels': False, 'infer_dtype': 'auto', 'hf_hub_token': '<HF_HUB_TOKEN>', 'ms_hub_token': '<MS_HUB_TOKEN>', 'om_hub_token': '<OM_HUB_TOKEN>', 'print_param_status': False, 'trust_remote_code': True, 'quantization_method': 'BNB', 'quantization_bit': None, 'quantization_type': 'nf4', 'double_quantization': True, 'quantization_device_map': None, 'image_max_pixels': 589824, 'image_min_pixels': 1024, 'image_do_pan_and_scan': False, 'crop_to_patches': False, 'video_max_pixels': 65536, 'video_min_pixels': 256, 'video_fps': 2.0, 'video_maxlen': 128, 'use_audio_in_video': False, 'audio_sampling_rate': 16000, 'export_dir': None, 'export_size': 5, 'export_device': 'cpu', 'export_quantization_bit': None, 'export_quantization_dataset': None, 'export_quantization_nsamples': 128, 'export_quantization_maxlen': 1024, 'export_legacy_format': False, 'export_hub_model_id': None, 'use_kt': False, 'kt_optimize_rule': None, 'cpu_infer': 32, 'chunk_size': 8192, 'mode': 'normal', 'kt_maxlen': 4096, 'kt_use_cuda_graph': True, 'kt_mode': 'normal', 'kt_force_think': False, 'vllm_maxlen': 4096, 'vllm_gpu_util': 0.7, 'vllm_enforce_eager': False, 'vllm_max_lora_rank': 32, 'vllm_config': None, 'sglang_maxlen': 4096, 'sglang_mem_fraction': 0.7, 'sglang_tp_size': -1, 'sglang_config': None, 'sglang_lora_backend': 'triton', 'compute_dtype': 'torch.bfloat16', 'device_map': {'': 'cuda:0'}, 'model_max_length': 2047, 'block_diag_attn': False}, 'data_args': {'template': 'qwen3_nothink', 'dataset': ['Markie_Voss_t34_d300_r0'], 'eval_dataset': None, 'dataset_dir': '/workspace/LlamaFactory/data', 'media_dir': '/workspace/LlamaFactory/data', 'cutoff_len': 2047, 'train_on_prompt': False, 'mask_history': False, 'streaming': False, 'buffer_size': 16384, 'mix_strategy': 'concat', 'interleave_probs': None, 'overwrite_cache': False, 'preprocessing_batch_size': 1000, 'preprocessing_num_workers': 16, 'max_samples': 100000000, 'eval_num_beams': None, 'ignore_pad_token_for_loss': True, 'val_size': 0.0, 'eval_on_each_dataset': False, 'packing': True, 'neat_packing': False, 'tool_format': None, 'default_system': None, 'enable_thinking': False, 'tokenized_path': None, 'data_shared_file_system': False}, 'finetuning_args': {'freeze_trainable_layers': 2, 'freeze_trainable_modules': ['all'], 'freeze_extra_modules': None, 'additional_target': None, 'module_dropout': 0.0, 'oft_rank': 0, 'oft_block_size': 32, 'oft_target': ['all'], 'create_new_adapter': False, 'lora_alpha': 64, 'lora_dropout': 0.03, 'lora_rank': 32, 'lora_target': ['all'], 'loraplus_lr_ratio': None, 'loraplus_lr_embedding': 1e-06, 'use_rslora': False, 'use_dora': False, 'pissa_init': False, 'pissa_iter': 16, 'pissa_convert': False, 'pref_beta': 0.1, 'pref_ftx': 0.0, 'pref_bco_weight': 0.0, 'pref_loss': 'sigmoid', 'dpo_label_smoothing': 0.0, 'kto_chosen_weight': 1.0, 'kto_rejected_weight': 1.0, 'simpo_gamma': 0.5, 'ppo_buffer_size': 1, 'ppo_epochs': 4, 'ppo_score_norm': False, 'ppo_target': 6.0, 'ppo_whiten_rewards': False, 'ref_model': None, 'ref_model_adapters': None, 'ref_model_quantization_bit': None, 'reward_model': None, 'reward_model_adapters': None, 'reward_model_quantization_bit': None, 'reward_model_type': 'lora', 'ld_alpha': None, 'use_galore': False, 'galore_target': ['all'], 'galore_rank': 16, 'galore_update_interval': 200, 'galore_scale': 2.0, 'galore_proj_type': 'std', 'galore_layerwise': False, 'use_apollo': False, 'apollo_target': ['all'], 'apollo_rank': 16, 'apollo_update_interval': 200, 'apollo_scale': 32.0, 'apollo_proj': 'random', 'apollo_proj_type': 'std', 'apollo_scale_type': 'channel', 'apollo_layerwise': False, 'apollo_scale_front': False, 'use_badam': False, 'badam_mode': 'layer', 'badam_start_block': None, 'badam_switch_mode': 'ascending', 'badam_switch_interval': 50, 'badam_update_ratio': 0.05, 'badam_mask_mode': 'adjacent', 'badam_verbose': 0, 'use_swanlab': False, 'swanlab_project': 'llamafactory', 'swanlab_workspace': None, 'swanlab_run_name': None, 'swanlab_mode': 'cloud', 'swanlab_api_key': '<SWANLAB_API_KEY>', 'swanlab_logdir': None, 'swanlab_lark_webhook_url': None, 'swanlab_lark_secret': None, 'pure_bf16': False, 'stage': 'pt', 'finetuning_type': 'lora', 'use_llama_pro': False, 'use_adam_mini': False, 'use_mca': False, 'use_muon': False, 'use_dft_loss': False, 'use_eaft_loss': False, 'eaft_alpha': 1.0, 'freeze_vision_tower': True, 'freeze_multi_modal_projector': True, 'freeze_language_model': False, 'compute_accuracy': False, 'disable_shuffling': False, 'early_stopping_steps': None, 'plot_loss': True, 'include_effective_tokens_per_second': False}, 'generating_args': {'do_sample': True, 'temperature': 0.95, 'top_p': 0.7, 'top_k': 50, 'num_beams': 1, 'max_new_tokens': 1024, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'skip_special_tokens': True}}
+2026-02-12 10:15:26,287 INFO    wandb-AsyncioManager-main:874 [service_client.py:_forward_responses():94] Reached EOF.
+2026-02-12 10:15:26,288 INFO    wandb-AsyncioManager-main:874 [mailbox.py:close():154] Closing mailbox, abandoning 1 handles.
+2026-02-12 10:15:26,797 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,810 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,812 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,844 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,845 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,848 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,854 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,856 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,858 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,859 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,860 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,861 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,863 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,871 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,875 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,878 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,883 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,885 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,891 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,898 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,899 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,914 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,916 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,917 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost
+2026-02-12 10:15:26,921 ERROR   wandb-AsyncioManager-main:874 [asyncio_manager.py:fn_wrap_exceptions():183] Uncaught exception in run_soon callback.
+Traceback (most recent call last):
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/asyncio_manager.py", line 181, in fn_wrap_exceptions
+    await fn()
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 38, in publish
+    await self._send_server_request(request)
+  File "/usr/local/lib/python3.11/dist-packages/wandb/sdk/lib/service/service_client.py", line 64, in _send_server_request
+    await self._writer.drain()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 392, in drain
+    await self._protocol._drain_helper()
+  File "/usr/lib/python3.11/asyncio/streams.py", line 166, in _drain_helper
+    raise ConnectionResetError('Connection lost')
+ConnectionResetError: Connection lost

LlamaFactory/wandb/run-20260211_035539-7vgn4sn5/files/config.yaml

@@ -0,0 +1,723 @@
+_name_or_path:
+    value: /workspace/Qwen/Qwen3-8B-Base
+_wandb:
+    value:
+        cli_version: 0.24.2
+        e:
+            d932fckwajkbgds6xb39j0rfceozuncf:
+                args:
+                    - /workspace/v127rc_exp2/B_mup.yaml
+                cpu_count: 24
+                cpu_count_logical: 48
+                cudaVersion: "12.8"
+                disk:
+                    /:
+                        total: "21474836480"
+                        used: "2406432768"
+                email: markmochi200@gmail.com
+                executable: /usr/bin/python
+                git:
+                    commit: 1a02717fa84c270d1c156c4c4a391c2f95525a63
+                    remote: https://github.com/hiyouga/LlamaFactory.git
+                gpu: NVIDIA GeForce RTX 4090
+                gpu_count: 1
+                gpu_nvidia:
+                    - architecture: Ada
+                      cudaCores: 16384
+                      memoryTotal: "25757220864"
+                      name: NVIDIA GeForce RTX 4090
+                      uuid: GPU-d934067c-f87d-c530-801b-ffb9d79da646
+                host: 4760e22a4db4
+                memory:
+                    total: "270098481152"
+                os: Linux-6.8.0-79-generic-x86_64-with-glibc2.35
+                program: /usr/local/bin/llamafactory-cli
+                python: CPython 3.11.10
+                root: /workspace/LlamaFactory
+                startedAt: "2026-02-11T03:55:39.815654Z"
+                writerId: d932fckwajkbgds6xb39j0rfceozuncf
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.11.10
+        t:
+            "1":
+                - 1
+                - 11
+                - 41
+                - 49
+                - 51
+                - 71
+                - 84
+                - 98
+                - 105
+            "2":
+                - 1
+                - 11
+                - 41
+                - 49
+                - 51
+                - 71
+                - 84
+                - 98
+                - 105
+            "3":
+                - 7
+                - 19
+                - 62
+                - 66
+            "4": 3.11.10
+            "5": 0.24.2
+            "6": 5.0.0
+            "9":
+                "1": transformers_trainer
+            "12": 0.24.2
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.95
+adam_epsilon:
+    value: 1e-08
+architectures:
+    value:
+        - Qwen3ForCausalLM
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: null
+chunk_size_feed_forward:
+    value: 0
+data_args:
+    value:
+        buffer_size: 16384
+        cutoff_len: 2047
+        data_shared_file_system: false
+        dataset:
+            - Markie_Voss_t34_d300_r0
+        dataset_dir: /workspace/LlamaFactory/data
+        default_system: null
+        enable_thinking: false
+        eval_dataset: null
+        eval_num_beams: null
+        eval_on_each_dataset: false
+        ignore_pad_token_for_loss: true
+        interleave_probs: null
+        mask_history: false
+        max_samples: 100000000
+        media_dir: /workspace/LlamaFactory/data
+        mix_strategy: concat
+        neat_packing: false
+        overwrite_cache: false
+        packing: true
+        preprocessing_batch_size: 1000
+        preprocessing_num_workers: 16
+        streaming: false
+        template: qwen3_nothink
+        tokenized_path: null
+        tool_format: null
+        train_on_prompt: false
+        val_size: 0
+data_seed:
+    value: null
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 180000000
+debug:
+    value: []
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: false
+do_predict:
+    value: false
+do_train:
+    value: true
+dtype:
+    value: bfloat16
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 151645
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: null
+eval_strategy:
+    value: "no"
+eval_use_gather_object:
+    value: false
+finetuning_args:
+    value:
+        additional_target: null
+        apollo_layerwise: false
+        apollo_proj: random
+        apollo_proj_type: std
+        apollo_rank: 16
+        apollo_scale: 32
+        apollo_scale_front: false
+        apollo_scale_type: channel
+        apollo_target:
+            - all
+        apollo_update_interval: 200
+        badam_mask_mode: adjacent
+        badam_mode: layer
+        badam_start_block: null
+        badam_switch_interval: 50
+        badam_switch_mode: ascending
+        badam_update_ratio: 0.05
+        badam_verbose: 0
+        compute_accuracy: false
+        create_new_adapter: false
+        disable_shuffling: false
+        dpo_label_smoothing: 0
+        eaft_alpha: 1
+        early_stopping_steps: null
+        finetuning_type: lora
+        freeze_extra_modules: null
+        freeze_language_model: false
+        freeze_multi_modal_projector: true
+        freeze_trainable_layers: 2
+        freeze_trainable_modules:
+            - all
+        freeze_vision_tower: true
+        galore_layerwise: false
+        galore_proj_type: std
+        galore_rank: 16
+        galore_scale: 2
+        galore_target:
+            - all
+        galore_update_interval: 200
+        include_effective_tokens_per_second: false
+        kto_chosen_weight: 1
+        kto_rejected_weight: 1
+        ld_alpha: null
+        lora_alpha: 64
+        lora_dropout: 0.03
+        lora_rank: 32
+        lora_target:
+            - all
+        loraplus_lr_embedding: 1e-06
+        loraplus_lr_ratio: null
+        module_dropout: 0
+        oft_block_size: 32
+        oft_rank: 0
+        oft_target:
+            - all
+        pissa_convert: false
+        pissa_init: false
+        pissa_iter: 16
+        plot_loss: true
+        ppo_buffer_size: 1
+        ppo_epochs: 4
+        ppo_score_norm: false
+        ppo_target: 6
+        ppo_whiten_rewards: false
+        pref_bco_weight: 0
+        pref_beta: 0.1
+        pref_ftx: 0
+        pref_loss: sigmoid
+        pure_bf16: false
+        ref_model: null
+        ref_model_adapters: null
+        ref_model_quantization_bit: null
+        reward_model: null
+        reward_model_adapters: null
+        reward_model_quantization_bit: null
+        reward_model_type: lora
+        simpo_gamma: 0.5
+        stage: pt
+        swanlab_api_key: <SWANLAB_API_KEY>
+        swanlab_lark_secret: null
+        swanlab_lark_webhook_url: null
+        swanlab_logdir: null
+        swanlab_mode: cloud
+        swanlab_project: llamafactory
+        swanlab_run_name: null
+        swanlab_workspace: null
+        use_adam_mini: false
+        use_apollo: false
+        use_badam: false
+        use_dft_loss: false
+        use_dora: false
+        use_eaft_loss: false
+        use_galore: false
+        use_llama_pro: false
+        use_mca: false
+        use_muon: false
+        use_rslora: false
+        use_swanlab: false
+fp8:
+    value: false
+fp8_backend:
+    value: auto
+fp8_enable_fsdp_float8_all_gather:
+    value: false
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+full_determinism:
+    value: false
+generating_args:
+    value:
+        do_sample: true
+        length_penalty: 1
+        max_new_tokens: 1024
+        num_beams: 1
+        repetition_penalty: 1
+        skip_special_tokens: true
+        temperature: 0.95
+        top_k: 50
+        top_p: 0.7
+generation_config:
+    value: null
+generation_max_length:
+    value: 2047
+generation_num_beams:
+    value: null
+gradient_accumulation_steps:
+    value: 8
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+group_by_length:
+    value: false
+head_dim:
+    value: 128
+hidden_act:
+    value: silu
+hidden_size:
+    value: 4096
+hub_always_push:
+    value: false
+hub_model_id:
+    value: null
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: all
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 12288
+is_encoder_decoder:
+    value: false
+label_names:
+    value:
+        - labels
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+layer_types:
+    value:
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+learning_rate:
+    value: 0.0001
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_dir:
+    value: null
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 1
+logging_strategy:
+    value: steps
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: cosine
+master_addr:
+    value: null
+master_port:
+    value: null
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 32768
+max_steps:
+    value: -1
+max_window_layers:
+    value: 36
+metric_for_best_model:
+    value: null
+model/num_parameters:
+    value: 8278029312
+model_args:
+    value:
+        adapter_folder: null
+        adapter_name_or_path: null
+        add_special_tokens: null
+        add_tokens: null
+        audio_sampling_rate: 16000
+        block_diag_attn: false
+        cache_dir: null
+        chunk_size: 8192
+        compute_dtype: torch.bfloat16
+        cpu_infer: 32
+        crop_to_patches: false
+        device_map:
+            "": cuda:0
+        disable_gradient_checkpointing: false
+        double_quantization: true
+        enable_liger_kernel: false
+        export_device: cpu
+        export_dir: null
+        export_hub_model_id: null
+        export_legacy_format: false
+        export_quantization_bit: null
+        export_quantization_dataset: null
+        export_quantization_maxlen: 1024
+        export_quantization_nsamples: 128
+        export_size: 5
+        flash_attn: auto
+        hf_hub_token: <HF_HUB_TOKEN>
+        image_do_pan_and_scan: false
+        image_max_pixels: 589824
+        image_min_pixels: 1024
+        infer_backend: HF
+        infer_dtype: auto
+        init_special_tokens: noise_init
+        kt_force_think: false
+        kt_maxlen: 4096
+        kt_mode: normal
+        kt_optimize_rule: null
+        kt_use_cuda_graph: true
+        low_cpu_mem_usage: true
+        mixture_of_depths: null
+        mode: normal
+        model_max_length: 2047
+        model_name_or_path: /workspace/Qwen/Qwen3-8B-Base
+        model_revision: main
+        moe_aux_loss_coef: null
+        ms_hub_token: <MS_HUB_TOKEN>
+        new_special_tokens_config: null
+        offload_folder: offload
+        om_hub_token: <OM_HUB_TOKEN>
+        print_param_status: false
+        quantization_bit: null
+        quantization_device_map: null
+        quantization_method: BNB
+        quantization_type: nf4
+        resize_vocab: false
+        rope_scaling: null
+        sglang_config: null
+        sglang_lora_backend: triton
+        sglang_maxlen: 4096
+        sglang_mem_fraction: 0.7
+        sglang_tp_size: -1
+        shift_attn: false
+        split_special_tokens: false
+        train_from_scratch: false
+        trust_remote_code: true
+        upcast_layernorm: false
+        upcast_lmhead_output: false
+        use_audio_in_video: false
+        use_fast_tokenizer: true
+        use_kt: false
+        use_kv_cache: true
+        use_reentrant_gc: true
+        use_unsloth: false
+        use_unsloth_gc: false
+        use_v1_kernels: false
+        video_fps: 2
+        video_max_pixels: 65536
+        video_maxlen: 128
+        video_min_pixels: 256
+        vllm_config: null
+        vllm_enforce_eager: false
+        vllm_gpu_util: 0.7
+        vllm_max_lora_rank: 32
+        vllm_maxlen: 4096
+model_type:
+    value: qwen3
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 32
+num_hidden_layers:
+    value: 36
+num_key_value_heads:
+    value: 8
+num_train_epochs:
+    value: 10
+optim:
+    value: adamw_torch
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: /workspace/v127rc_exp2/B_mup
+output_hidden_states:
+    value: false
+overwrite_output_dir:
+    value: false
+pad_token_id:
+    value: 151643
+parallelism_config:
+    value: null
+peft_config:
+    value:
+        default:
+            alora_invocation_tokens: null
+            arrow_config: null
+            auto_mapping: null
+            base_model_name_or_path: /workspace/Qwen/Qwen3-8B-Base
+            bias: none
+            corda_config: null
+            ensure_weight_tying: false
+            eva_config: null
+            exclude_modules: null
+            fan_in_fan_out: false
+            inference_mode: false
+            init_lora_weights: true
+            layer_replication: null
+            layers_pattern: null
+            layers_to_transform: null
+            lora_alpha: 64
+            lora_bias: false
+            lora_dropout: 0.03
+            megatron_config: null
+            megatron_core: megatron.core
+            modules_to_save: null
+            peft_type: LORA
+            peft_version: 0.18.1
+            qalora_group_size: 16
+            r: 32
+            revision: null
+            runtime_config:
+                ephemeral_gpu_offload: false
+            target_modules:
+                - q_proj
+                - v_proj
+                - down_proj
+                - up_proj
+                - gate_proj
+                - k_proj
+                - o_proj
+            target_parameters: null
+            task_type: CAUSAL_LM
+            trainable_token_indices: null
+            use_dora: false
+            use_qalora: false
+            use_rslora: false
+per_device_eval_batch_size:
+    value: 8
+per_device_train_batch_size:
+    value: 1
+predict_with_generate:
+    value: false
+prediction_loss_only:
+    value: false
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+ray_init_kwargs:
+    value: null
+ray_num_workers:
+    value: 1
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 1000000
+        rope_type: default
+run_name:
+    value: null
+save_on_each_node:
+    value: false
+save_only_model:
+    value: true
+save_steps:
+    value: 100
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+skip_memory_metrics:
+    value: true
+sliding_window:
+    value: null
+sortish_sampler:
+    value: false
+tf32:
+    value: null
+tie_word_embeddings:
+    value: false
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_space_id:
+    value: trackio
+transformers_version:
+    value: 5.0.0
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_liger_kernel:
+    value: false
+use_sliding_window:
+    value: false
+vocab_size:
+    value: 151936
+warmup_ratio:
+    value: 0.01
+warmup_steps:
+    value: 0.01
+weight_decay:
+    value: 0.01

LlamaFactory/wandb/run-20260211_035539-7vgn4sn5/files/wandb-metadata.json

@@ -0,0 +1,41 @@
+{
+  "os": "Linux-6.8.0-79-generic-x86_64-with-glibc2.35",
+  "python": "CPython 3.11.10",
+  "startedAt": "2026-02-11T03:55:39.815654Z",
+  "args": [
+    "/workspace/v127rc_exp2/B_mup.yaml"
+  ],
+  "program": "/usr/local/bin/llamafactory-cli",
+  "git": {
+    "remote": "https://github.com/hiyouga/LlamaFactory.git",
+    "commit": "1a02717fa84c270d1c156c4c4a391c2f95525a63"
+  },
+  "email": "markmochi200@gmail.com",
+  "root": "/workspace/LlamaFactory",
+  "host": "4760e22a4db4",
+  "executable": "/usr/bin/python",
+  "cpu_count": 24,
+  "cpu_count_logical": 48,
+  "gpu": "NVIDIA GeForce RTX 4090",
+  "gpu_count": 1,
+  "disk": {
+    "/": {
+      "total": "21474836480",
+      "used": "2406432768"
+    }
+  },
+  "memory": {
+    "total": "270098481152"
+  },
+  "gpu_nvidia": [
+    {
+      "name": "NVIDIA GeForce RTX 4090",
+      "memoryTotal": "25757220864",
+      "cudaCores": 16384,
+      "architecture": "Ada",
+      "uuid": "GPU-d934067c-f87d-c530-801b-ffb9d79da646"
+    }
+  ],
+  "cudaVersion": "12.8",
+  "writerId": "d932fckwajkbgds6xb39j0rfceozuncf"
+}

LlamaFactory/wandb/run-20260211_035539-7vgn4sn5/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_runtime":109185,"train/epoch":3.665927977839335,"train_runtime":109179.797,"train/loss":0.006374494172632694,"_wandb":{"runtime":109185},"_timestamp":1.7708913191638207e+09,"train/learning_rate":7.126525942172399e-05,"train/grad_norm":0.027281571179628372,"_step":13233,"train/num_input_tokens_seen":216719984,"train/train_tokens_per_second":1984.982,"train/global_step":13234}